frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a protocol for gathering context that includes reading a file named .impeccable.md from the project root. This presents an indirect prompt injection surface where external data is incorporated into the agent's reasoning process.
- Ingestion points: SKILL.md (Context Gathering Protocol) specifies checking for .impeccable.md in the project root.
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to treat this content as untrusted data.
- Capability inventory: The skill enables the agent to generate and refine production-grade frontend code (HTML, CSS, JS).
- Sanitization: There are no instructions for sanitizing or validating the contents of the context file.
Audit Metadata