frontend-design
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its protocol for gathering project context.\n
- Ingestion points: Reads project-specific design context from a file named
.impeccable.mdlocated in the project root (SKILL.md).\n - Boundary markers: Absent. The instructions direct the agent to 'proceed immediately' if the context file exists, without requiring delimiters or instructions to treat the content as data only.\n
- Capability inventory: The skill has the capability to generate and implement production-grade frontend code, including UI components and logic (SKILL.md).\n
- Sanitization: Absent. No validation, filtering, or escaping is performed on the content read from the
.impeccable.mdfile.
Audit Metadata