address-github-comments

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the official GitHub CLI (gh) to interact with pull requests. It provides instructions for executing commands such as gh pr view --comments and gh pr comment to manage feedback.
  • [EXTERNAL_DOWNLOADS]: References the author's public GitHub repository as the source for provenance and synchronization of the skill's logic. This is documented for transparency and auditability.
  • [PROMPT_INJECTION]: The skill ingests untrusted data in the form of GitHub comments. The provided workflow mitigates indirect prompt injection risks by requiring the agent to propose a plan and wait for explicit user confirmation before applying any changes or responding to threads.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — address-github-comments