production-readiness-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest external content from URLs or Pull Requests to perform its review. This ingestion point constitutes a surface area for indirect prompt injection if the external artifact contains adversarial instructions designed to influence the agent's output. However, the skill's specific scoring criteria and rigid output format provide significant structure that limits the effectiveness of such injections.\n- [EXTERNAL_DOWNLOADS]: The documentation references an external resource at frontendguide.dev for additional guidance on production risks. This link is used for reference purposes and does not involve automated script execution or package installation.
Audit Metadata