chro
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The instructions are focused on legitimate HR and talent strategy activities. The tool use is restricted to project-specific file modifications and standard web searches for compensation benchmarking.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from the
docs/people/directory, which establishes a data-processing surface.\n - Ingestion points: Local documentation in the
docs/people/path (referenced in SKILL.md).\n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data.\n
- Capability inventory: The agent has access to
WebSearch,Write, andEdittools, allowing it to move data and modify files based on its findings.\n - Sanitization: No explicit sanitization or validation logic is specified for the contents of the local files.
Audit Metadata