omh-people-ops
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a fair and evidence-based workflow for hiring decisions. It includes explicit safety constraints, such as keeping protected characteristics out of evaluations and avoiding unauthorized external HR actions.
- [NO_CODE]: This skill consists entirely of instructional markdown and metadata. There are no executable scripts or external dependencies included that could perform unauthorized operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted hiring and candidate data, creating a potential surface for indirect prompt injection. However, the lack of exploitable tools or capabilities makes the risk level safe.
- Ingestion points: Recruiting plans, candidate debriefs, and hiring context provided in user prompts (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are defined for user-provided evidence.
- Capability inventory: No scripts or tools for file system, network, or command execution are included.
- Sanitization: No input validation or sanitization is described.
Audit Metadata