Compare commits

..
27 Commits
Author SHA1 Message Date
GitHub Actions f4fb5c6cdc chore: bump Claude Code to 2.1.140 and Agent SDK to 0.2.140 2026-05-12 21:10:29 +00:00
GitHub Actions dde2242db6 chore: bump Claude Code to 2.1.139 and Agent SDK to 0.2.139 2026-05-11 18:44:48 +00:00
GitHub Actions 476e359e62 chore: bump Claude Code to 2.1.138 and Agent SDK to 0.2.138 2026-05-09 06:34:03 +00:00
GitHub Actions ad67978e5e chore: bump Claude Code to 2.1.137 and Agent SDK to 0.2.137 2026-05-09 00:11:30 +00:00
GitHub Actions 034cbdb008 chore: bump Claude Code to 2.1.136 and Agent SDK to 0.2.136 2026-05-08 18:39:38 +00:00
GitHub Actions 939ae9c056 chore: bump Claude Code to 2.1.133 and Agent SDK to 0.2.133 2026-05-07 23:49:29 +00:00
Octavian GuzuandGitHub e9c374db23 Update HackerOne links in SECURITY.md (#1268)
* Update HackerOne links in SECURITY.md

🏠 Remote-Dev: homespace

* Rename VDP heading to Anthropic Bug Bounty

🏠 Remote-Dev: homespace
2026-05-07 11:21:40 +01:00
GitHub Actions 9db782c3a1 chore: bump Claude Code to 2.1.132 and Agent SDK to 0.2.132 2026-05-06 22:09:09 +00:00
GitHub Actions 62238ddb33 chore: bump Claude Code to 2.1.131 and Agent SDK to 0.2.131 2026-05-06 07:48:07 +00:00
GitHub Actions 7d7d3055f1 chore: bump Claude Code to 2.1.129 and Agent SDK to 0.2.129 2026-05-06 01:40:52 +00:00
GitHub Actions 2cc1ac1331 chore: bump Claude Code to 2.1.128 and Agent SDK to 0.2.128 2026-05-04 23:02:42 +00:00
Justin BisignanoandGitHub 38f25dd747 fix: make trigger_phrase match case-insensitive (#1279)
GitHub @-mention autocomplete inserts @Claude (capitalized) when users
pick the bot from the dropdown, but the trigger regex had no 'i' flag,
so the action would log 'No trigger was met for @claude' and exit. The
workflow's outer 'if: contains(...)' gate is case-insensitive, so the
job runs and looks like it silently ignored the user.

The regex was case-sensitive since the initial commit with no test
asserting either behavior; the existing tests focus on word-boundary
precision ([email protected] etc.), not case.
2026-05-02 10:10:30 -07:00
GitHub Actions fefa07e9c6 chore: bump Claude Code to 2.1.126 and Agent SDK to 0.2.126 2026-05-01 02:05:59 +00:00
GitHub Actions ef50f123a3 chore: bump Claude Code to 2.1.123 and Agent SDK to 0.2.123 2026-04-29 03:29:24 +00:00
GitHub Actions b3c0320e7e chore: bump Claude Code to 2.1.122 and Agent SDK to 0.2.122 2026-04-28 22:05:53 +00:00
Octavian GuzuandGitHub c93e8fe879 docs: pull_request_target guidance and base-action trust model (#1250)
* docs: add pull_request_target/workflow_run guidance and base-action trust model

Adds a security.md section on safe checkout patterns under
pull_request_target/workflow_run, and a trust-model section to the
base-action README clarifying that callers are responsible for the
working directory and prompt being trusted.

🏠 Remote-Dev: homespace

* docs: refine PRT/workflow_run guidance — root checkout + workflow_run ref

Second example now checks out the base ref at the workspace root before
the head-ref subdirectory checkout (this action expects a git repo at
the root). Adds the workflow_run ref form, drops the PRT-specific
gh-pr-diff hint from the first example, and generalises the closing
line to cover both event types.

🏠 Remote-Dev: homespace

* docs: use actions/checkout@v6 in examples (consistency)

🏠 Remote-Dev: homespace
2026-04-28 10:01:48 -07:00
GitHub Actions 11a9dadd19 chore: bump Claude Code to 2.1.121 and Agent SDK to 0.2.121 2026-04-28 00:31:46 +00:00
GitHub Actions 567fe954a4 chore: bump Claude Code to 2.1.119 and Agent SDK to 0.2.119 2026-04-25 01:55:30 +00:00
GitHub Actions 2da6cfae68 chore: bump Claude Code to 2.1.120 and Agent SDK to 0.2.120 2026-04-25 00:15:05 +00:00
GitHub Actions e58dfa5555 chore: bump Claude Code to 2.1.119 and Agent SDK to 0.2.119 2026-04-23 23:24:21 +00:00
6ee201f023 fix: allow + in branch names (generated by Claude Code EnterWorktree) (#1248)
Claude Code's EnterWorktree tool converts "/" to "+" when generating
branch names from worktree names (e.g. EnterWorktree("feat/foo") creates
branch "worktree-feat+foo"). The strict whitelist in validateBranchName
rejected these names, causing claude-code-action to fail on any PR opened
from an EnterWorktree-generated branch.

Since all git calls use execFileSync (not shell interpolation), "+" carries
no command injection risk — the same rationale used for allowing "#".
Git itself permits "+" in branch names per git-check-ref-format.

Fixes: https://github.com/anthropics/claude-code-action/issues/1244

Co-authored-by: Claude Sonnet 4.6 <[email protected]>
2026-04-22 22:17:44 -07:00
GitHub Actions b4d6741327 chore: bump Claude Code to 2.1.118 and Agent SDK to 0.2.118 2026-04-23 00:42:34 +00:00
GitHub Actions 4e5d8b13ca chore: bump Claude Code to 2.1.117 and Agent SDK to 0.2.117 2026-04-22 00:04:56 +00:00
GitHub Actions 5d5c10a4f3 chore: bump Claude Code to 2.1.116 and Agent SDK to 0.2.116 2026-04-20 22:18:45 +00:00
Octavian GuzuandGitHub 632a368e81 docs: nit updates to security.md (#1240)
🏠 Remote-Dev: homespace
2026-04-20 15:00:35 +01:00
Ashwin BhatandGitHub 4c682d8b65 chore: bump oven-sh/setup-bun to v2.2.0 (Node.js 24) (#1238)
setup-bun v2.1.2 runs on Node.js 20, which GitHub will stop supporting
on June 2, 2026. v2.2.0 updates the action runtime to Node.js 24.

Fixes #1237
2026-04-19 17:53:46 -07:00
GitHub Actions 38ec876110 chore: bump Claude Code to 2.1.114 and Agent SDK to 0.2.114 2026-04-18 01:38:24 +00:00
14 changed files with 93 additions and 34 deletions
+3 -3
View File
@@ -8,8 +8,8 @@ This repository is maintained by [Anthropic](https://www.anthropic.com/).
The security of our systems and user data is Anthropic’s top priority. We appreciate the work of security researchers acting in good faith in identifying and reporting potential vulnerabilities.
Our security program is managed on HackerOne and we ask that any validated vulnerability in this functionality be reported through their [submission form](https://hackerone.com/anthropic-vdp/reports/new?type=team&report_type=vulnerability).
Our security program is managed on HackerOne and we ask that any validated vulnerability in this functionality be reported through their [submission form](https://hackerone.com/4f1f16ba-10d3-4d09-9ecc-c721aad90f24/embedded_submissions/new).
## Vulnerability Disclosure Program
## Anthropic Bug Bounty
Our Vulnerability Program Guidelines are defined on our [HackerOne program page](https://hackerone.com/anthropic-vdp).
Our Bug Bounty Program Guidelines are defined on our [HackerOne program page](https://hackerone.com/anthropic).
+1 -1
View File
@@ -173,7 +173,7 @@ runs:
steps:
- name: Install Bun
if: inputs.path_to_bun_executable == ''
uses: oven-sh/setup-bun@3d267786b128fe76c2f16a390aa2448b815359f3 # https://github.com/oven-sh/setup-bun/releases/tag/v2.1.2
uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # https://github.com/oven-sh/setup-bun/releases/tag/v2.2.0
with:
bun-version: 1.3.6
token: ${{ inputs.github_token || github.token }}
+8
View File
@@ -4,6 +4,14 @@ This GitHub Action allows you to run [Claude Code](https://www.anthropic.com/cla
For simply tagging @claude in issues and PRs out of the box, [check out the Claude Code action and GitHub app](https://github.com/anthropics/claude-code-action).
## Trust model
This action is a thin wrapper that installs and runs Claude Code with the inputs you provide. It does **not** enforce any trust boundaries on its own. Running this action in a directory is equivalent to running Claude Code in that directory — Claude reads project-level configuration (`.claude/`, `CLAUDE.md`, `.mcp.json`, etc.) from the working directory, and the action's own setup steps run from there as well.
**The caller is responsible for ensuring the working directory and prompt are trusted.** If your workflow processes untrusted input (issues, fork pull requests, external comments), use [`anthropics/claude-code-action`](https://github.com/anthropics/claude-code-action) instead — it provides actor permission checks, restores project configuration from the base ref in PR contexts, and is the supported path for those scenarios.
See [Claude Code's security documentation](https://docs.anthropic.com/en/docs/claude-code/security) and the [GitHub Actions guidance on `pull_request_target`](https://securitylab.github.com/research/github-actions-preventing-pwn-requests/) for background.
## Usage
Add the following to your workflow file:
+2 -2
View File
@@ -97,7 +97,7 @@ runs:
- name: Install Bun
if: inputs.path_to_bun_executable == ''
uses: oven-sh/setup-bun@3d267786b128fe76c2f16a390aa2448b815359f3 # https://github.com/oven-sh/setup-bun/releases/tag/v2.1.2
uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # https://github.com/oven-sh/setup-bun/releases/tag/v2.2.0
with:
bun-version: 1.3.6
@@ -124,7 +124,7 @@ runs:
PATH_TO_CLAUDE_CODE_EXECUTABLE: ${{ inputs.path_to_claude_code_executable }}
run: |
if [ -z "$PATH_TO_CLAUDE_CODE_EXECUTABLE" ]; then
CLAUDE_CODE_VERSION="2.1.113"
CLAUDE_CODE_VERSION="2.1.140"
echo "Installing Claude Code v${CLAUDE_CODE_VERSION}..."
for attempt in 1 2 3; do
echo "Installation attempt $attempt..."
+10 -10
View File
@@ -6,7 +6,7 @@
"name": "@anthropic-ai/claude-code-base-action",
"dependencies": {
"@actions/core": "^1.10.1",
"@anthropic-ai/claude-agent-sdk": "^0.2.113",
"@anthropic-ai/claude-agent-sdk": "^0.2.140",
"shell-quote": "^1.8.3",
},
"devDependencies": {
@@ -27,23 +27,23 @@
"@actions/io": ["@actions/[email protected]", "", {}, "sha512-wi9JjgKLYS7U/z8PPbco+PvTb/nRWjeoFlJ1Qer83k/3C5PHQi28hiVdeE2kHXmIL99mQFawx8qt/JPjZilJ8Q=="],
"@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/[email protected]13", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.2.113", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.2.113" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-TMeZeBDTdGNZek2VvRB4zCCFkJHbqKU1dn+OG3wms9h8z/DUKuDAUvjmmQCXP9c4K2ipPS1WmmRJljXRcKfStg=="],
"@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/[email protected]40", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.2.140", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.2.140" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-Zq2L7YCoTdbxTUi3/soN1axrTqbG7GoKuc6Im8EpkBRdwaY0D1W9+Ux3vAbV/cX8Qk31Vck7DQLZz1lGEArdoQ=="],
"@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "darwin", "cpu": "arm64" }, "sha512-FymNWXlee9xID6AKU/aWjeIzlMTL7LAtVVL5kg2j3MYm7o8lfTY996cEN1ulWXeF7i3pVbzYtIzE+avhVDauPA=="],
"@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "darwin", "cpu": "arm64" }, "sha512-zEbDsDKeoDO4DzbyX6wBVlcPhLy/gYiCrKzKnxmkOhyNtJBeshgiOTdr+M7WX1xcuI/M/UhEY+B9U6oo884lAQ=="],
"@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/[email protected]13", "", { "os": "darwin", "cpu": "x64" }, "sha512-pST/cJunx8mup8RxnuCTQNmwyli4/LcvmLVPaZgVSYchLQlBCE26bQKZwdoeMc/+F7Gm/eBt8Yz53GTTqV3TMA=="],
"@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/[email protected]40", "", { "os": "darwin", "cpu": "x64" }, "sha512-BFJGeZEksvERy7mMJ0mkNAWoMrZOgl6XN/mKPaunGnaC/i+1ykx7xih7e58bRhsrzKzo2mnUrwtjiFyF3MFNRQ=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "arm64" }, "sha512-QMkDOEfOMg8W/PLAHnp3cU9wLWp/RvJuVlrwn5s4Oei/bP3kxfuV0uLoxXUZZNSnv2lcplxAKUGgOz7Xa0asFw=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "arm64" }, "sha512-FauGGg3zikxrjAUnu+Pso6zD9Qv4Z2+QBiTiZqc12U+x4uoikNsplymUnsJ7MYD9VaTGmLJuZ9pCch0IiKrseQ=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "arm64" }, "sha512-nXKJmIrxbgXMIE2fKebJVAFJiFqb6LsyzfxYn/tqgkYNfqk6IBDX+cP6eV5qRE72sNHI1E/ogF72N5MjhNeOHA=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "arm64" }, "sha512-nG7xLL0nKb4ymFVnX0QhSGLoyhh9fuuDpBR+TYz5O4ZQc2RVUMSMqGusqcCNEIGxAKQSVKWCf0WgpCG/edAO9Q=="],
"@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "x64" }, "sha512-/CQz7jiOp98hfrLwDJvmfPXtGCuWFGr+j7Zbi40uHovd5+TXJ1fOZNMEdb4aVKW3KYPbxA1aT6XNP8nAgmuPvA=="],
"@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "x64" }, "sha512-7f627Tq2mIiwFoBYfCKTdEeZSP90r8UOWu/I5DezudTtwtoVl2zRaRCnJ8c4rW+Tzw+xWSfP/pHvR9bTQGXaOw=="],
"@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "x64" }, "sha512-PGpstZ8mWEQfCjDd+qV/rPsdLLkzFobINPpLr4ALMu8fQMEEs5SsabumGup48fnK3Z19/WlfI9FC1iVzxsE3LQ=="],
"@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "x64" }, "sha512-EZ7VzOGmvft/1ymh2rwts5v3yPnsGGlGrTJlY2Dqnr1ABF43JIhEm1NFYrLnXQWSN74s5Pj8tgkPbYS9x4BhFA=="],
"@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "win32", "cpu": "arm64" }, "sha512-NqtFDTVPg7fh+yee7KnsVZ/MZ6VogE+dQcIobEN0NVl03i5pbQAWfSZNOEvhk2XyEaJ4rdk+/9MPED+UThF5gQ=="],
"@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "win32", "cpu": "arm64" }, "sha512-9EOozRF+LTt3UedeJtjJXC8pj9VTAFtPBuB+/YUmcpmDAEH9qcWWknWhf7NDKTapKtBWkNP/387x+18L15MLqg=="],
"@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/[email protected]13", "", { "os": "win32", "cpu": "x64" }, "sha512-0VoW/fTkygn/uZqPhOPjmXaVc1H3wkNNJd/fMyWKDR2p76Y9loQPQZk2R5tNRWlK5mDo65F6+Omby0rCx9XtQw=="],
"@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/[email protected]40", "", { "os": "win32", "cpu": "x64" }, "sha512-puQyWoYiqosjDEYULWAS/lBJse1vzib0NmQj/bYTirWCbtiUcu6ixKMd4NmLbE+Si/DKTB8XNz6hVZ/KckqeoQ=="],
"@anthropic-ai/sdk": ["@anthropic-ai/[email protected]", "", { "dependencies": { "json-schema-to-ts": "^3.1.1" }, "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["zod"], "bin": { "anthropic-ai-sdk": "bin/cli" } }, "sha512-D4K5PvEV6wPiRtVlVsJHIUhHAmOZ6IT/I9rKlTf84gR7GyyAurPJK7z9BOf/AZqC5d1DhYQGJNKRmV+q8dGhgw=="],
+1 -1
View File
@@ -11,7 +11,7 @@
},
"dependencies": {
"@actions/core": "^1.10.1",
"@anthropic-ai/claude-agent-sdk": "^0.2.113",
"@anthropic-ai/claude-agent-sdk": "^0.2.140",
"shell-quote": "^1.8.3"
},
"devDependencies": {
+10 -10
View File
@@ -7,7 +7,7 @@
"dependencies": {
"@actions/core": "^1.10.1",
"@actions/github": "^6.0.1",
"@anthropic-ai/claude-agent-sdk": "^0.2.113",
"@anthropic-ai/claude-agent-sdk": "^0.2.140",
"@modelcontextprotocol/sdk": "^1.11.0",
"@octokit/graphql": "^8.2.2",
"@octokit/rest": "^21.1.1",
@@ -37,23 +37,23 @@
"@actions/io": ["@actions/[email protected]", "", {}, "sha512-wi9JjgKLYS7U/z8PPbco+PvTb/nRWjeoFlJ1Qer83k/3C5PHQi28hiVdeE2kHXmIL99mQFawx8qt/JPjZilJ8Q=="],
"@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/[email protected]13", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.2.113", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.2.113", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.2.113", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.2.113" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-TMeZeBDTdGNZek2VvRB4zCCFkJHbqKU1dn+OG3wms9h8z/DUKuDAUvjmmQCXP9c4K2ipPS1WmmRJljXRcKfStg=="],
"@anthropic-ai/claude-agent-sdk": ["@anthropic-ai/[email protected]40", "", { "dependencies": { "@anthropic-ai/sdk": "^0.81.0", "@modelcontextprotocol/sdk": "^1.29.0" }, "optionalDependencies": { "@anthropic-ai/claude-agent-sdk-darwin-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-darwin-x64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-arm64-musl": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-x64": "0.2.140", "@anthropic-ai/claude-agent-sdk-linux-x64-musl": "0.2.140", "@anthropic-ai/claude-agent-sdk-win32-arm64": "0.2.140", "@anthropic-ai/claude-agent-sdk-win32-x64": "0.2.140" }, "peerDependencies": { "zod": "^4.0.0" } }, "sha512-Zq2L7YCoTdbxTUi3/soN1axrTqbG7GoKuc6Im8EpkBRdwaY0D1W9+Ux3vAbV/cX8Qk31Vck7DQLZz1lGEArdoQ=="],
"@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "darwin", "cpu": "arm64" }, "sha512-FymNWXlee9xID6AKU/aWjeIzlMTL7LAtVVL5kg2j3MYm7o8lfTY996cEN1ulWXeF7i3pVbzYtIzE+avhVDauPA=="],
"@anthropic-ai/claude-agent-sdk-darwin-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "darwin", "cpu": "arm64" }, "sha512-zEbDsDKeoDO4DzbyX6wBVlcPhLy/gYiCrKzKnxmkOhyNtJBeshgiOTdr+M7WX1xcuI/M/UhEY+B9U6oo884lAQ=="],
"@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/[email protected]13", "", { "os": "darwin", "cpu": "x64" }, "sha512-pST/cJunx8mup8RxnuCTQNmwyli4/LcvmLVPaZgVSYchLQlBCE26bQKZwdoeMc/+F7Gm/eBt8Yz53GTTqV3TMA=="],
"@anthropic-ai/claude-agent-sdk-darwin-x64": ["@anthropic-ai/[email protected]40", "", { "os": "darwin", "cpu": "x64" }, "sha512-BFJGeZEksvERy7mMJ0mkNAWoMrZOgl6XN/mKPaunGnaC/i+1ykx7xih7e58bRhsrzKzo2mnUrwtjiFyF3MFNRQ=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "arm64" }, "sha512-QMkDOEfOMg8W/PLAHnp3cU9wLWp/RvJuVlrwn5s4Oei/bP3kxfuV0uLoxXUZZNSnv2lcplxAKUGgOz7Xa0asFw=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "arm64" }, "sha512-FauGGg3zikxrjAUnu+Pso6zD9Qv4Z2+QBiTiZqc12U+x4uoikNsplymUnsJ7MYD9VaTGmLJuZ9pCch0IiKrseQ=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "arm64" }, "sha512-nXKJmIrxbgXMIE2fKebJVAFJiFqb6LsyzfxYn/tqgkYNfqk6IBDX+cP6eV5qRE72sNHI1E/ogF72N5MjhNeOHA=="],
"@anthropic-ai/claude-agent-sdk-linux-arm64-musl": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "arm64" }, "sha512-nG7xLL0nKb4ymFVnX0QhSGLoyhh9fuuDpBR+TYz5O4ZQc2RVUMSMqGusqcCNEIGxAKQSVKWCf0WgpCG/edAO9Q=="],
"@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "x64" }, "sha512-/CQz7jiOp98hfrLwDJvmfPXtGCuWFGr+j7Zbi40uHovd5+TXJ1fOZNMEdb4aVKW3KYPbxA1aT6XNP8nAgmuPvA=="],
"@anthropic-ai/claude-agent-sdk-linux-x64": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "x64" }, "sha512-7f627Tq2mIiwFoBYfCKTdEeZSP90r8UOWu/I5DezudTtwtoVl2zRaRCnJ8c4rW+Tzw+xWSfP/pHvR9bTQGXaOw=="],
"@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/[email protected]13", "", { "os": "linux", "cpu": "x64" }, "sha512-PGpstZ8mWEQfCjDd+qV/rPsdLLkzFobINPpLr4ALMu8fQMEEs5SsabumGup48fnK3Z19/WlfI9FC1iVzxsE3LQ=="],
"@anthropic-ai/claude-agent-sdk-linux-x64-musl": ["@anthropic-ai/[email protected]40", "", { "os": "linux", "cpu": "x64" }, "sha512-EZ7VzOGmvft/1ymh2rwts5v3yPnsGGlGrTJlY2Dqnr1ABF43JIhEm1NFYrLnXQWSN74s5Pj8tgkPbYS9x4BhFA=="],
"@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/[email protected]13", "", { "os": "win32", "cpu": "arm64" }, "sha512-NqtFDTVPg7fh+yee7KnsVZ/MZ6VogE+dQcIobEN0NVl03i5pbQAWfSZNOEvhk2XyEaJ4rdk+/9MPED+UThF5gQ=="],
"@anthropic-ai/claude-agent-sdk-win32-arm64": ["@anthropic-ai/[email protected]40", "", { "os": "win32", "cpu": "arm64" }, "sha512-9EOozRF+LTt3UedeJtjJXC8pj9VTAFtPBuB+/YUmcpmDAEH9qcWWknWhf7NDKTapKtBWkNP/387x+18L15MLqg=="],
"@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/[email protected]13", "", { "os": "win32", "cpu": "x64" }, "sha512-0VoW/fTkygn/uZqPhOPjmXaVc1H3wkNNJd/fMyWKDR2p76Y9loQPQZk2R5tNRWlK5mDo65F6+Omby0rCx9XtQw=="],
"@anthropic-ai/claude-agent-sdk-win32-x64": ["@anthropic-ai/[email protected]40", "", { "os": "win32", "cpu": "x64" }, "sha512-puQyWoYiqosjDEYULWAS/lBJse1vzib0NmQj/bYTirWCbtiUcu6ixKMd4NmLbE+Si/DKTB8XNz6hVZ/KckqeoQ=="],
"@anthropic-ai/sdk": ["@anthropic-ai/[email protected]", "", { "dependencies": { "json-schema-to-ts": "^3.1.1" }, "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["zod"], "bin": { "anthropic-ai-sdk": "bin/cli" } }, "sha512-D4K5PvEV6wPiRtVlVsJHIUhHAmOZ6IT/I9rKlTf84gR7GyyAurPJK7z9BOf/AZqC5d1DhYQGJNKRmV+q8dGhgw=="],
+34 -1
View File
@@ -15,11 +15,44 @@
- Is designed for automation workflows where user permissions are already restricted by the workflow's permission scope
- When set, Claude does a best-effort scrub of Anthropic, cloud, and GitHub Actions secrets from subprocess environments. On Linux runners with bubblewrap available, subprocesses additionally run with PID-namespace isolation. This reduces but does not eliminate prompt injection risk — keep workflow permissions minimal and validate all outputs. Set `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB: 0` in your workflow or job `env:` block to opt out.
- Optionally set `CLAUDE_CODE_SCRIPT_CAPS` in your workflow `env:` block to limit how many times Claude can call specific scripts per run. Value is JSON: `{"script-name.sh": maxCalls}`. Example: `CLAUDE_CODE_SCRIPT_CAPS: '{"edit-issue-labels.sh":2}'` allows at most 2 calls to `edit-issue-labels.sh`. Useful for write-capable helper scripts.
- When using `allowed_non_write_users`, always pass `github_token: ${{ secrets.GITHUB_TOKEN }}`. The auto-generated workflow token is scoped to the job's declared permissions and expires when the job completes. **Do not use a personal access token** — a static token does not rotate between runs, and depending on the tools allowed via `claude_args`, the model could be used to recover part or all of it. We recommend restricting allowed tools (e.g. `claude_args: '--allowedTools "Bash(gh issue view:*)"'`) to the minimum required when using `allowed_non_write_users`.
- When using `allowed_non_write_users`, always pass `github_token: ${{ secrets.GITHUB_TOKEN }}`. The auto-generated workflow token is scoped to the job's declared permissions and expires when the job completes. **Do not use a personal access token** — a static token does not rotate between runs and could be partially or fully recovered over time via prompt injection. Restricting allowed tools via `claude_args` reduces the rate of recovery but may not eliminate the risk. We recommend restricting allowed tools (e.g. `claude_args: '--allowedTools "Bash(gh issue view:*)"'`) to the minimum required when using `allowed_non_write_users`.
- **Token Permissions**: The GitHub app receives only a short-lived token scoped specifically to the repository it's operating in
- **No Cross-Repository Access**: Each action invocation is limited to the repository where it was triggered
- **Limited Scope**: The token cannot access other repositories or perform actions beyond the configured permissions
## Using this action with `pull_request_target` or `workflow_run`
`pull_request_target` and `workflow_run` execute with the **base repository's secrets**. If your workflow checks out the PR head (`ref: ${{ github.event.pull_request.head.sha }}` for `pull_request_target`, `ref: ${{ github.event.workflow_run.head_sha }}` for `workflow_run`) into `$GITHUB_WORKSPACE` before this action, the action and Claude run with that checkout as the working directory.
**Do not check out an untrusted ref into the workspace root before this action.** Use one of these patterns instead:
```yaml
# Preferred — check out the base ref (default).
- uses: actions/checkout@v6 # no `ref:` → base branch
- uses: anthropics/claude-code-action@v1
```
```yaml
# If you need the PR's files locally — check out the base ref at the workspace
# root (this action expects a git repo there), then check out the head ref into
# a subdirectory and pass it via --add-dir.
- uses: actions/checkout@v6 # no `ref:` → base branch at workspace root
- uses: actions/checkout@v6
with:
# For workflow_run use: ${{ github.event.workflow_run.head_sha }}
ref: ${{ github.event.pull_request.head.sha }}
path: pr-head
- uses: anthropics/claude-code-action@v1
with:
claude_args: "--add-dir pr-head"
```
This is general guidance for these event types — see [GitHub's documentation](https://securitylab.github.com/research/github-actions-preventing-pwn-requests/).
### `claude-code-action` vs `claude-code-base-action`
`claude-code-base-action` is a lower-level building block that installs and runs Claude Code with the inputs you provide. It does not perform actor permission checks or restore project configuration from the base ref. If you need those behaviors, use this action (`claude-code-action`). See the [base-action README](../base-action/README.md#trust-model) for details.
## Pull Request Creation
In its default configuration, **Claude does not create pull requests automatically** when responding to `@claude` mentions. Instead:
+1 -1
View File
@@ -12,7 +12,7 @@
"dependencies": {
"@actions/core": "^1.10.1",
"@actions/github": "^6.0.1",
"@anthropic-ai/claude-agent-sdk": "^0.2.113",
"@anthropic-ai/claude-agent-sdk": "^0.2.140",
"@modelcontextprotocol/sdk": "^1.11.0",
"@octokit/graphql": "^8.2.2",
"@octokit/rest": "^21.1.1",
+1 -1
View File
@@ -65,7 +65,7 @@ async function installClaudeCode(): Promise<string> {
return customExecutable;
}
const claudeCodeVersion = "2.1.113";
const claudeCodeVersion = "2.1.140";
console.log(`Installing Claude Code v${claudeCodeVersion}...`);
for (let attempt = 1; attempt <= 3; attempt++) {
+6 -4
View File
@@ -58,14 +58,16 @@ export function validateBranchName(branchName: string): void {
);
}
// Strict whitelist pattern: alphanumeric start, then alphanumeric/slash/hyphen/underscore/period/hash.
// Strict whitelist pattern: alphanumeric start, then alphanumeric/slash/hyphen/underscore/period/hash/plus.
// # is valid per git-check-ref-format and commonly used in branch names like "fix/#123-description".
// All git calls use execFileSync (not shell interpolation), so # carries no injection risk.
const validPattern = /^[a-zA-Z0-9][a-zA-Z0-9/_.#-]*$/;
// + is valid per git-check-ref-format and generated by Claude Code's EnterWorktree tool when
// converting worktree names containing "/" (e.g. "feat/foo" becomes "worktree-feat+foo").
// All git calls use execFileSync (not shell interpolation), so neither # nor + carries injection risk.
const validPattern = /^[a-zA-Z0-9][a-zA-Z0-9/_.#+-]*$/;
if (!validPattern.test(branchName)) {
throw new Error(
`Invalid branch name: "${branchName}". Branch names must start with an alphanumeric character and contain only alphanumeric characters, forward slashes, hyphens, underscores, periods, or hashes (#).`,
`Invalid branch name: "${branchName}". Branch names must start with an alphanumeric character and contain only alphanumeric characters, forward slashes, hyphens, underscores, periods, hashes (#), or plus signs (+).`,
);
}
+4
View File
@@ -51,6 +51,7 @@ export function checkContainsTrigger(context: ParsedGitHubContext): boolean {
// Check for exact match with word boundaries or punctuation
const regex = new RegExp(
`(^|\\s)${escapeRegExp(triggerPhrase)}([\\s.,!?;:]|$)`,
"i",
);
// Check in body
@@ -77,6 +78,7 @@ export function checkContainsTrigger(context: ParsedGitHubContext): boolean {
// Check for exact match with word boundaries or punctuation
const regex = new RegExp(
`(^|\\s)${escapeRegExp(triggerPhrase)}([\\s.,!?;:]|$)`,
"i",
);
// Check in body
@@ -105,6 +107,7 @@ export function checkContainsTrigger(context: ParsedGitHubContext): boolean {
// Check for exact match with word boundaries or punctuation
const regex = new RegExp(
`(^|\\s)${escapeRegExp(triggerPhrase)}([\\s.,!?;:]|$)`,
"i",
);
if (regex.test(reviewBody)) {
console.log(
@@ -125,6 +128,7 @@ export function checkContainsTrigger(context: ParsedGitHubContext): boolean {
// Check for exact match with word boundaries or punctuation
const regex = new RegExp(
`(^|\\s)${escapeRegExp(triggerPhrase)}([\\s.,!?;:]|$)`,
"i",
);
if (regex.test(commentBody)) {
console.log(`Comment contains exact trigger phrase '${triggerPhrase}'`);
+2
View File
@@ -186,6 +186,8 @@ describe("checkContainsTrigger", () => {
{ issueBody: "@claude: here's the issue", expected: true },
{ issueBody: "@claude; and another thing", expected: true },
{ issueBody: "Hey @claude, can you help?", expected: true },
{ issueBody: "@Claude can you help?", expected: true },
{ issueBody: "@CLAUDE fix this", expected: true },
{ issueBody: "claudette contains claude", expected: false },
{ issueBody: "[email protected]", expected: false },
];
+10
View File
@@ -45,6 +45,16 @@ describe("validateBranchName", () => {
).not.toThrow();
expect(() => validateBranchName("fix/issue-#42")).not.toThrow();
});
it("should accept branch names containing + (generated by Claude Code EnterWorktree)", () => {
// EnterWorktree converts "/" in worktree names to "+" when generating branch names.
// e.g. EnterWorktree("feat/skill-consolidation") → branch "worktree-feat+skill-consolidation"
expect(() =>
validateBranchName("worktree-feat+skill-consolidation"),
).not.toThrow();
expect(() => validateBranchName("fix+issue-123")).not.toThrow();
expect(() => validateBranchName("feature+new-thing")).not.toThrow();
});
});
describe("command injection attempts", () => {