git-helpers
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform Git and GitHub CLI operations. This includes commands for staging files, committing changes, pushing branches, and merging pull requests, which are consistent with its primary purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from git repositories. 1. Ingestion points: Data is read from git diffs, logs, and pull request titles as specified in instructions/commit.md, instructions/create-pull-request.md, and instructions/merge-pull-request.md. 2. Boundary markers: The skill uses instructions in references/message-sourcing.md to warn the agent against following instructions embedded in the processed data. 3. Capability inventory: The SKILL.md file allows for extensive shell command execution using the Bash tool for various git operations. 4. Sanitization: No programmatic sanitization or filtering of the external data is performed before it is analyzed by the agent.
Audit Metadata