address-pr-comments
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run project-specific verification scripts (e.g., lint, test, build) identified in local files such as CLAUDE.md, AGENTS.md, or the README.md.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes pull request comment bodies which could contain adversarial instructions.
- Ingestion points: The skill uses
gh api graphqlto fetch thebodyof review comments inSKILL.md. - Boundary markers: Absent. There are no instructions or delimiters to treat the comment content as untrusted data.
- Capability inventory: The agent can modify the file system via the
/implementcommand, interact with the GitHub API via theghtool, and execute local shell commands. - Sanitization: Absent. The skill triages and acts on comment text directly without filtering or escaping.
Audit Metadata