frontend-design-spec
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill processes user-provided feature requirements documents and transforms them into a specific design output. \n- Ingestion points: Feature requirements documents provided by the user in the agent context as described in SKILL.md. \n- Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions to separate the task logic from potentially malicious commands embedded in the input requirements. \n- Capability inventory: The skill is explicitly instructed to write output to a local project file path at
.dev/frontend_design_doc.md. \n- Sanitization: No input validation or sanitization is required for the requirements documents before the agent processes them into the final design specification.
Audit Metadata