peach-release
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
Bashtool to execute shell commands for Git and the GitHub CLI (gh). These commands are used to manage local and remote repository states, including branch switching, committing code, and managing pull requests. The skill instructions specify that it should only be used within the intended 'peach-harness' repository environment. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes untrusted data from commit logs and diffs to generate release documentation.
- Ingestion points: Commit messages and code differences are read via
git logandgit diff(SKILL.md). - Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the data being summarized.
- Capability inventory: The agent has access to
Bash,Write, andEdittools, enabling it to modify the repository and interact with remote APIs. - Sanitization: There is no evidence of sanitization for the commit data before it is processed by the agent. However, the risk is mitigated by a mandatory user review step before any summary is used or any command is executed.
Audit Metadata