frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads from local project configuration files such as .better-web-ui.md, .better-ui.md, and .impeccable.md (Ingestion points: SKILL.md). No boundary markers are present to delimit this untrusted content from the system instructions. The skill has capabilities to generate architectural and implementation code across multiple frameworks (Capability inventory: SKILL.md, reference/README.md). No sanitization logic for the ingested content was detected.
- [NO_CODE]: The skill contains no executable code, scripts, or binaries. It consists entirely of markdown documentation and YAML metadata meant to guide the agent's behavior.
- [SAFE]: Heuristic detections for prompt injection patterns were found to be false positives; the skill's instructions specifically warn against the use of 'concealment' and 'dark patterns' in user interface design.
Audit Metadata