excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user concepts to generate diagram elements, creating a surface for embedded instructions. However, the risk is minimized by the skill's specific output format and lack of dangerous capabilities. Ingestion points: User prompts (SKILL.md). Boundary markers: Absent. Capability inventory: File writing (.excalidraw). Sanitization: Absent.
- [NO_CODE]: The skill consists exclusively of instructional text and JSON schema templates; no executable code or scripts are present.
Audit Metadata