Skills
Navigate
skills/foraefactory/antigravity-skills/address-github-comments/Gen Agent Trust Hub

address-github-comments

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub pull request comments, which originate from external sources and could contain malicious instructions.
  • Ingestion points: Comments are fetched via gh pr view --comments in SKILL.md.
  • Boundary markers: The workflow explicitly includes a safety step: "Wait for user confirmation on which comments to address first".
  • Capability inventory: The agent can modify code and execute gh CLI commands.
  • Sanitization: Relies on human-in-the-loop review before taking action on feedback.
  • [COMMAND_EXECUTION]: The skill uses the official GitHub CLI (gh) to interact with pull requests, which is necessary for its functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:22 AM