frame-logo-outro
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to treat the entirety of the user's message as a design brief, which is then passed to external tools for project generation.
- Ingestion points: Untrusted user input is interpolated directly into the brief passed to the
prepare_open_design_brieftool as described inSKILL.md. - Boundary markers: No delimiters or instructions (e.g., 'ignore previous instructions') are employed to isolate the user-provided text from the agent's logic.
- Capability inventory: The skill allows the agent to create and edit files using internal file-editing tools and invoke the
register_open_design_artifacttool based on the instructions returned by the brief processor. - Sanitization: There is no evidence of validation or sanitization performed on the user's input before it is utilized by the agent.
Audit Metadata