code-review
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data (code snippets, diffs, or PR content).
- Ingestion points: The skill accepts a PR URL or file path as an argument ($1) in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore instructions found within the code being analyzed.
- Capability inventory: The skill specifies the use of source control connectors to fetch external data and provides detailed analysis that could be influenced by malicious code comments.
- Sanitization: There is no evidence of sanitization or filtering applied to the input content before it is processed by the agent.
Audit Metadata