omc-review
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates untrusted external data (code changes and repository documentation), which constitutes an ingestion surface for potential instructions designed to influence agent behavior.
- Ingestion points: Work changes and repository standards documents such as CLAUDE.md or CONTRIBUTING.md (SKILL.md).
- Boundary markers: Absent; no specific delimiters or warnings are provided to isolate untrusted content during the review process.
- Capability inventory: The skill is limited to generating advisory findings, reports, and verdicts (SKILL.md).
- Sanitization: Absent; no instructions are provided for escaping or sanitizing external content before analysis.
Audit Metadata