dec
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a static dispatcher for internal design engineering principles. It does not perform any sensitive operations such as file access, network requests, or command execution.
- [INDIRECT_PROMPT_INJECTION]: This skill ingests user-provided task descriptions to route to other skills. Evidence chain: 1. Ingestion points: user arguments or task descriptions per SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Loading other design-focused canon skills via the 'Skill tool'. 4. Sanitization: None. The surface is low-risk as it only influences structural instruction loading.
Audit Metadata