non-functional-test-planning
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 a formatted test plan, creating a potential surface for instructions to be injected into the agent's workflow.\n- Ingestion points: User-provided product journeys, SLO targets, and threat models collected in the Phase 1 setup section of SKILL.md.\n- Boundary markers: The skill does not use delimiters or specific instructions to isolate user data from its internal logic.\n- Capability inventory: The skill is designed to generate markdown documents and diagrams and save them to a user-specified path (defaulting to /documentation/ in SKILL.md).\n- Sanitization: No explicit input validation or escaping is performed on user inputs before they are interpolated into the final report.
Audit Metadata