security-assessments
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides informational guidance and templates for security compliance. The included Python script (scripts/check-output.py) is a local utility for validating report content and does not perform network operations or access sensitive data in an unsafe manner.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information to generate security deliverables, which presents a surface for indirect prompt injection.
- Ingestion points: User-provided data interpolated into templates/output-template.md.
- Boundary markers: None present in the output template to distinguish between instructions and data.
- Capability inventory: Local script execution via scripts/check-output.py for content validation.
- Sanitization: No explicit sanitization or validation of user-provided content before interpolation.
Audit Metadata