spec-interviewer
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The specification generation process creates an indirect prompt injection surface.
- Ingestion points: User answers are collected via the
AskUserQuestiontool as described in Phase 1, 2, and 3 ofSKILL.md. - Boundary markers: The output markdown template for
tasks/spec-YYYYMMDD-{slug}.mddoes not include delimiters or clear instructions to isolate user input from agent instructions. - Capability inventory: The skill uses the
Writetool to create the spec file, and the instructions explicitly direct the user to load the resulting file in a new session where the agent will act upon the requirements. - Sanitization: No sanitization or escaping is performed on the user's responses before they are saved to the filesystem.
Audit Metadata