pr
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run git and gh commands for branch state evaluation, pushing changes, and creating pull requests.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests and summarizes commit history which could contain malicious instructions.
- Ingestion points: Git log and git diff commands used in SKILL.md to retrieve commit data.
- Boundary markers: No boundary markers or instructions are provided to the agent to isolate or ignore potential commands within the commit messages.
- Capability inventory: Access to the Bash tool and the GitHub CLI (gh) as specified in SKILL.md.
- Sanitization: No validation or sanitization is performed on the ingested git data before the agent processes it for the PR summary.
Audit Metadata