specs-kit-spec-check
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including adversarial review reports and project-level architecture/ontology documents to generate user questions and update specification files.
- Ingestion points: Content is loaded from various markdown files including
docs/specs/,adversarial-review/*.md,architecture.md, andontology.md. - Boundary markers: The skill lacks explicit boundary markers or instructions to disregard potential hidden instructions within the ingested markdown files.
- Capability inventory: The skill has the capability to read and write markdown files and conduct an interactive dialogue with the user.
- Sanitization: There is no evidence of sanitization or filtering of content from review findings (e.g., suggested fixes) before it is integrated into the specification or presented as a question.
Audit Metadata