baseline-ui
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains configuration and guidelines for enforcing UI standards (Tailwind CSS, typography, layout, animation). It does not include any scripts, executable code, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts file inputs to review against UI constraints, creating a potential surface for indirect prompt injection from untrusted code files.
- Ingestion points: Reviews external files provided via the
/baseline-ui <file>command (SKILL.md). - Boundary markers: Absent; there are no specific delimiters to separate user code from agent instructions.
- Capability inventory: The skill has no high-privilege capabilities; it is limited to providing text-based reviews and code suggestions.
- Sanitization: Absent.
Audit Metadata