design-system
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Potential for indirect prompt injection via external file ingestion. The skill processes user-controlled DESIGN.md files which could contain hidden instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads content from 'DESIGN.md' (as described in SKILL.md) during the 'load' and 'validate' actions.
- Boundary markers: SKILL.md does not define any delimiters or explicit 'ignore instructions' markers to separate design data from potential malicious prompts within the design document.
- Capability inventory: According to SKILL.md, the skill can inject file content into the agent's context and perform filesystem-wide compliance scans.
- Sanitization: There is no evidence of sanitization or filtering of the design document content to prevent the execution of embedded natural language instructions.
Audit Metadata