skills/aivokone/ak-skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it retrieves content from external, potentially untrusted sources.\n
  • Ingestion points: scripts/check-pr-feedback.sh, scripts/check-new-feedback.sh, and scripts/wait-for-reviews.sh fetch raw comment and review text from the GitHub API.\n
  • Boundary markers: The scripts provide output structure using text headers (e.g., '📝 NEW CONVERSATION COMMENTS') and triple-dash ('---') separators between entries.\n
  • Capability inventory: The skill allows the agent to commit code, push to remote repositories, and execute project-specific test and build commands.\n
  • Sanitization: No programmatic sanitization is applied to the fetched text; the skill relies on instructional guidance warning the agent to verify all feedback before acting on it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 11:26 AM