security-requirements-classification
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate documentation, representing an indirect prompt injection surface.
- Ingestion points: User-provided parameters for 'Subject', 'Data assets', and 'Functional assets' defined in Phase 1 of SKILL.md.
- Boundary markers: Absent; the skill does not use specific delimiters or instructions to separate user-provided content from the agent's logic.
- Capability inventory: SKILL.md specifies a file-writing operation in Phase 11 to save the generated security report.
- Sanitization: Absent; the instructions do not include mechanisms for validating or escaping user-provided asset names or descriptions.
Audit Metadata