review-security
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content such as pull requests and infrastructure changes. While this presents an attack surface where malicious instructions could be embedded in the code being reviewed, the skill includes explicit guardrails to operate read-only and avoid sensitive data access, which mitigates the risk of the agent acting on such injections.\n
- Ingestion points: Processes application and infrastructure changes provided for review as mentioned in SKILL.md.\n
- Boundary markers: The skill does not define specific delimiters for the external content it processes to isolate it from the agent instructions.\n
- Capability inventory: The instructions restrict the agent to read-only analysis and sandboxed testing (SKILL.md), and forbid access to production systems or private credentials.\n
- Sanitization: No explicit sanitization of input data is defined within the skill instructions.
Audit Metadata