design-critique
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external files such as brand guidelines and design system tokens, which introduces an attack surface where malicious instructions embedded in those files could influence the agent's behavior.\n
- Ingestion points: The 'Prerequisites' section in SKILL.md directs the agent to read 'design-context files' for brand guidelines and tokens.\n
- Boundary markers: The instructions do not define any boundary markers or delimiters to separate external data from system instructions, nor do they include warnings to ignore instructions found within that data.\n
- Capability inventory: The skill generates specific CSS and HTML code recommendations based on the content of the ingested files.\n
- Sanitization: The skill does not implement or mention any sanitization, filtering, or validation for the content read from external files.
Audit Metadata