use-design-system
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from websites and repositories, creating an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to inspect 'Website or live reference', 'Existing app or repo', and 'Screenshots' to derive design rules (SKILL.md, Section 1).
- Boundary markers: The instructions do not provide guidance on using delimiters or explicit 'ignore' warnings for content found in these external sources.
- Capability inventory: The agent is authorized to 'Read code' (SKILL.md, Section 1) and use 'UI automation' or 'documentation workflows' which may involve system interaction or network access (SKILL.md, Section 3).
- Sanitization: The instructions lack specific steps for sanitizing or validating the retrieved external content before the agent acts upon it.
Audit Metadata