clarify
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to perform static analysis and refinement of software design documents. All operations are confined to the local project documentation paths (e.g.,
02-DOCS/wiki/sdd/). - [INDIRECT_PROMPT_INJECTION]: The skill has a natural attack surface as it processes external data from specification files (
02-DOCS/wiki/sdd/specs/*.md) and user profiles. - Ingestion points: Specification files, project constitution, and user profiles are read into the agent context in
SKILL.md(Read first section). - Boundary markers: None explicitly defined in the instructions, though it focuses on specific typed handoff sections.
- Capability inventory: The skill performs file-write operations to 'bake' answers back into the spec documents.
- Sanitization: Not present.
- This surface is typical for document processing skills and does not escalate the verdict as it is tied to the primary intended purpose of the skill.
Audit Metadata