code-review
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 process untrusted external data, such as code diffs and pull request content. While this presents a surface for indirect prompt injection where code comments or content could attempt to influence the agent, the risk is negligible as the skill does not utilize any tools or capabilities that could be exploited.\n
- Ingestion points: Content from pull requests and code audits provided by the user in the prompt context.\n
- Boundary markers: None specified in the instructions.\n
- Capability inventory: No tool access, shell execution, or network capabilities defined.\n
- Sanitization: No input filtering or escaping is applied to the analyzed code.- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected within the skill instructions.
Audit Metadata