frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): The skill uses 'CRITICAL' and 'IMPORTANT' markers, but they are applied to design principles and aesthetic choices rather than attempting to bypass safety filters or override system instructions.
- [Data Exposure & Exfiltration] (SAFE): No patterns found for accessing sensitive local files (~/.ssh, .env) or transmitting data to external domains.
- [Unverifiable Dependencies] (SAFE): No package managers (npm, pip) or remote script execution patterns (curl|bash) are utilized. The mention of the 'Motion' library is a design suggestion for the generated output, not a dependency of the skill itself.
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process user-provided frontend requirements.
- Ingestion points: User-provided frontend requirements in 'SKILL.md'.
- Boundary markers: Absent; the skill does not define specific delimiters to separate user input from the rest of the generation logic.
- Capability inventory: The skill is limited to generating code (HTML/CSS/JS, React, Vue). It lacks capabilities for subprocess execution, file system modification, or network requests.
- Sanitization: Absent; the skill relies on the underlying LLM's safety filters.
Audit Metadata