org-health-diagnostic
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFENO_CODECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill references an external Python script ('scripts/health_scorer.py') and a reference file ('references/health-benchmarks.md') which are not included in the provided file set.
- [COMMAND_EXECUTION]: The instructions describe executing a local Python script ('health_scorer.py') to process metrics.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection via user-supplied metrics. 1. Ingestion points: User-provided organizational metrics. 2. Boundary markers: Absent. 3. Capability inventory: Local script execution. 4. Sanitization: Absent.
Audit Metadata