mockup-device-3d
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to 'Treat the rest of the user's message as the brief', which is then passed to the
prepare_open_design_brieftool. This content eventually guides the agent's file-editing behavior. - Ingestion points: The user's input message is used as the primary data source for the design brief.
- Boundary markers: The skill lacks explicit delimiters (e.g., XML tags or triple backticks) to isolate user-provided content from the system instructions.
- Capability inventory: The skill utilizes
prepare_open_design_brief,list_open_design_design_systems,recommend_open_design_design_systems, andregister_open_design_artifactfrom an MCP server, along with the agent's native file-editing tools. - Sanitization: There is no evidence of content validation or escaping of user input before it is interpolated into the design brief.
Audit Metadata