design-system
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection due to its processing of untrusted data.
- Ingestion points: Reads local CSS/styling files (SKILL.md) and fetches content from external URLs for competitor research (via browser MCP) and site auditing (--url parameter).
- Boundary markers: Absent; there are no delimiters or instructions to the agent to ignore potentially malicious instructions embedded in the design files or external site content.
- Capability inventory: The skill possesses file-write capabilities, generating
DESIGN.md,design-tokens.json, and an interactivedesign-preview.htmlfile based on the analysis. - Sanitization: The skill description does not specify any sanitization or validation of the data retrieved from external URLs or local files before it is processed or used in file generation.
Audit Metadata