code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external code, which is a source of untrusted data.\n
- Ingestion points: Source code provided to the agent for review in SKILL.md.\n
- Boundary markers: Absent; the instructions do not specify delimiters for untrusted code content.\n
- Capability inventory: No scripts or external tools are requested or defined in this skill.\n
- Sanitization: Absent; the skill does not specify input validation or sanitization protocols for the analyzed code content.
Audit Metadata