Compare commits

...

12 Commits

Author SHA1 Message Date
Claude
9e388ead50 Add Australian programming joke to README
Added a light-hearted programming joke with an Australian twist to the README,
referencing both coding bugs and drop bears for some local flavor.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-06 22:27:45 +00:00
GitHub Actions
ac1a3207f3 chore: bump Claude Code version to 2.0.9 2025-10-06 21:57:24 +00:00
Ashwin Bhat
521d069da7 docs: add prompt injection security note (#604)
* docs: add prompt injection security note

Add warning about potential hidden markdown in untrusted content from external contributors. Documents existing sanitization measures while acknowledging new bypass techniques may emerge.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Update docs/security.md

Co-authored-by: David Dworken <dworken@anthropic.com>

* format

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: David Dworken <dworken@anthropic.com>
2025-10-06 09:51:50 -07:00
GitHub Actions
7e4b782d5f chore: bump Claude Code version to 2.0.8 2025-10-04 23:17:33 +00:00
GitHub Actions
4fb0ef3be0 chore: bump Claude Code version to 2.0.5 2025-10-02 19:29:43 +00:00
GitHub Actions
14ac8aa20e chore: bump Claude Code version to 2.0.1 2025-10-01 02:30:10 +00:00
Ashwin Bhat
90d189f3ab fix: update permission test prompts to trigger actual tool usage (#596)
Changed test prompts from communication-style echo commands to legitimate
technical operations. This ensures Claude attempts the Bash tool call
(which then gets blocked by permissions) instead of refusing based on
communication guidelines.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <noreply@anthropic.com>
2025-09-30 18:04:13 -07:00
GitHub Actions
9c09b26b2d chore: bump Claude Code version to 2.0.2 2025-10-01 00:48:36 +00:00
GitHub Actions
2086c977a5 chore: bump Claude Code version to 2.0.1 2025-09-30 02:45:30 +00:00
GitHub Actions
851ef5b84e chore: bump Claude Code version to 2.0.0 2025-09-29 16:45:58 +00:00
Song Huang
1ce8153c18 docs: fix the faq doc link (#593) 2025-09-28 10:02:17 -07:00
GitHub Actions
00391ab25e chore: bump Claude Code version to 1.0.128 2025-09-27 16:44:46 +00:00
6 changed files with 11 additions and 5 deletions

View File

@@ -67,7 +67,7 @@ jobs:
uses: ./base-action uses: ./base-action
with: with:
prompt: | prompt: |
Use Bash to echo "This should not work" Run the command `echo $HOME` to check the home directory path
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }} anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
settings: | settings: |
{ {
@@ -163,7 +163,7 @@ jobs:
uses: ./base-action uses: ./base-action
with: with:
prompt: | prompt: |
Use Bash to echo "This should not work from file" Run the command `echo $HOME` to check the home directory path
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }} anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
settings: "test-settings.json" settings: "test-settings.json"

View File

@@ -2,6 +2,8 @@
# Claude Code Action # Claude Code Action
> *Why do Aussie programmers prefer dark mode? Because the light brings in drop bears and bugs, mate!* 🐨🐛
A general-purpose [Claude Code](https://claude.ai/code) action for GitHub PRs and issues that can answer questions and implement code changes. This action intelligently detects when to activate based on your workflow context—whether responding to @claude mentions, issue assignments, or executing automation tasks with explicit prompts. It supports multiple authentication methods including Anthropic direct API, Amazon Bedrock, and Google Vertex AI. A general-purpose [Claude Code](https://claude.ai/code) action for GitHub PRs and issues that can answer questions and implement code changes. This action intelligently detects when to activate based on your workflow context—whether responding to @claude mentions, issue assignments, or executing automation tasks with explicit prompts. It supports multiple authentication methods including Anthropic direct API, Amazon Bedrock, and Google Vertex AI.
## Features ## Features

View File

@@ -177,7 +177,7 @@ runs:
# Install Claude Code if no custom executable is provided # Install Claude Code if no custom executable is provided
if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then
echo "Installing Claude Code..." echo "Installing Claude Code..."
curl -fsSL https://claude.ai/install.sh | bash -s 1.0.127 curl -fsSL https://claude.ai/install.sh | bash -s 2.0.9
echo "$HOME/.local/bin" >> "$GITHUB_PATH" echo "$HOME/.local/bin" >> "$GITHUB_PATH"
else else
echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}" echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}"

View File

@@ -99,7 +99,7 @@ runs:
run: | run: |
if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then if [ -z "${{ inputs.path_to_claude_code_executable }}" ]; then
echo "Installing Claude Code..." echo "Installing Claude Code..."
curl -fsSL https://claude.ai/install.sh | bash -s 1.0.127 curl -fsSL https://claude.ai/install.sh | bash -s 2.0.9
else else
echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}" echo "Using custom Claude Code executable: ${{ inputs.path_to_claude_code_executable }}"
# Add the directory containing the custom executable to PATH # Add the directory containing the custom executable to PATH

View File

@@ -13,6 +13,10 @@
- **No Cross-Repository Access**: Each action invocation is limited to the repository where it was triggered - **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 - **Limited Scope**: The token cannot access other repositories or perform actions beyond the configured permissions
## ⚠️ Prompt Injection Risks
**Beware of potential hidden markdown when tagging Claude on untrusted content.** External contributors may include hidden instructions through HTML comments, invisible characters, hidden attributes, or other techniques. The action sanitizes content by stripping HTML comments, invisible characters, markdown image alt text, hidden HTML attributes, and HTML entities, but new bypass techniques may emerge. We recommend reviewing the raw content of all input coming from external contributors before allowing Claude to process it.
## GitHub App Permissions ## GitHub App Permissions
The [Claude Code GitHub app](https://github.com/apps/claude) requires these permissions: The [Claude Code GitHub app](https://github.com/apps/claude) requires these permissions:

View File

@@ -709,7 +709,7 @@ What You CANNOT Do:
- Modify files in the .github/workflows directory (GitHub App permissions do not allow workflow modifications) - Modify files in the .github/workflows directory (GitHub App permissions do not allow workflow modifications)
When users ask you to perform actions you cannot do, politely explain the limitation and, when applicable, direct them to the FAQ for more information and workarounds: When users ask you to perform actions you cannot do, politely explain the limitation and, when applicable, direct them to the FAQ for more information and workarounds:
"I'm unable to [specific action] due to [reason]. You can find more information and potential workarounds in the [FAQ](https://github.com/anthropics/claude-code-action/blob/main/FAQ.md)." "I'm unable to [specific action] due to [reason]. You can find more information and potential workarounds in the [FAQ](https://github.com/anthropics/claude-code-action/blob/main/docs/faq.md)."
If a user asks for something outside these capabilities (and you have no other tools provided), politely explain that you cannot perform that action and suggest an alternative approach if possible. If a user asks for something outside these capabilities (and you have no other tools provided), politely explain that you cannot perform that action and suggest an alternative approach if possible.