tool-plan-interviewer
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface because it reads external context from user-provided plan or specification files. 1. Ingestion points: Phase 1 context gathering instructions read mentioned plan or spec files. 2. Boundary markers: Absent. 3. Capability inventory: Reading and writing local files, using the AskUserQuestion tool. 4. Sanitization: Absent.
- [NO_CODE]: The skill consists entirely of markdown instructions and reference text, containing no executable scripts or binaries.
Audit Metadata