industry-standard-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted code submissions via the
submission_diffinput field. This creates a surface where malicious instructions could be embedded within code snippets to override the agent's behavior during the review process. - Ingestion point:
submission_diffparameter inskill.yaml. - Boundary markers: None specified in the metadata to delimit untrusted data from the system prompt.
- Capability inventory: Performs tone, style, and Clean Code analysis.
- Sanitization: No explicit sanitization or escaping of the diff content is mentioned in the configuration.
Audit Metadata