spec-kit-specify
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to generate project specifications, which introduces a surface for indirect instructions to be stored in the resulting files.
- Ingestion points: Natural language feature descriptions provided by the user in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or warning markers for the user-supplied content within the generated spec.md file.
- Capability inventory: The skill is instructed to create directories and write files to the local filesystem under the 'specs/changes/' path.
- Sanitization: The instructions include a 'Derive a kebab-case name' step which mitigates path traversal, and guardrails to prevent implementation details from being included, although no explicit filtering for malicious prompt instructions is present.
Audit Metadata