address-github-comments

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external text from GitHub comments, creating a potential surface for indirect prompt injection attacks where instructions could be hidden in review feedback.\n
  • Ingestion points: Fetches review threads and issue comments using gh pr view --comments as described in SKILL.md.\n
  • Boundary markers: The workflow explicitly requires the agent to "Wait for user confirmation" before addressing comments or applying fixes.\n
  • Capability inventory: The agent is authorized to modify the local codebase and execute commands via the GitHub CLI.\n
  • Sanitization: No explicit sanitization, escaping, or validation of the fetched comment content is specified.\n- [COMMAND_EXECUTION]: The skill uses the official GitHub CLI (gh) to interact with pull requests, including viewing comments and posting resolutions. These commands are standard for the tool's purpose and are executed within a structured workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 05:29 PM
Security Audit — agent-trust-hub — address-github-comments