cmd-speckit-clarify
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes potentially untrusted data from local project files and user input.
- Ingestion points: The agent reads
spec.md, files within.specify/specs/*/, and.specify/memory/constitution.md, as well as processing user input via the{{INPUT}}placeholder. - Boundary markers: The skill lacks explicit boundary markers or delimiters to isolate untrusted file content from the system instructions.
- Capability inventory: The skill has the capability to read local files, modify/update specification files (Step 6), and invoke secondary commands like
/speckit.plan. - Sanitization: There is no evidence of input validation or sanitization of the content being read from the project files before it is incorporated into the agent's reasoning loop.
Audit Metadata