tailwind
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill files contain standard documentation, CSS templates, and instructions for working with Tailwind CSS v4. No malicious code, obfuscation, or unauthorized data exfiltration patterns were identified.- [INDIRECT_PROMPT_INJECTION]: The skill includes a feature to process user-provided Figma CSS variables and generate local theme files. This creates an attack surface for indirect prompt injection if the user-provided data contains hidden instructions. However, the risk is negligible as the agent is directed to follow a strict parsing and mapping workflow.
- Ingestion points: The user is prompted to paste Figma CSS variables into the chat in
rules/figma-to-theme-workflow.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the input data.
- Capability inventory: The workflow includes file-write operations to the
src/styles/figma-tokens/directory as described inrules/figma-to-theme-workflow.md. - Sanitization: The instructions emphasize parsing and classification logic but do not include explicit sanitization of the input content.
Audit Metadata