code-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external code repositories and pull request metadata.
- Ingestion points: The skill utilizes the Read, Grep, and Glob tools to fetch content from files and PR descriptions during its evaluation phases.
- Boundary markers: There are no instructions or delimiters defined to separate the skill's operational instructions from potentially adversarial content embedded in the code being reviewed.
- Capability inventory: The skill's potential for harm is mitigated by its restricted toolset (Read, Grep, Glob), which prevents network exfiltration or unauthorized file system modifications.
- Sanitization: No sanitization or validation logic is applied to the content retrieved from the workspace before it is processed by the agent.
Audit Metadata