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 graphql to fetch the body of review comments in SKILL.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 /implement command, interact with the GitHub API via the gh tool, and execute local shell commands.
  • Sanitization: Absent. The skill triages and acts on comment text directly without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 01:48 PM
Security Audit — agent-trust-hub — address-pr-comments