converting-css-to-tailwind
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and modifying external CSS and markup files, which creates a surface for indirect prompt injection.\n- Ingestion points: External CSS and markup files (HTML, JSX, TSX, Vue, Svelte) are read in workflow steps 1 and 2.\n- Boundary markers: There are no instructions for the agent to use boundary markers or to ignore instructions that might be embedded in the files being processed.\n- Capability inventory: The skill requires the agent to read, modify, and delete local files.\n- Sanitization: The skill does not provide any mechanisms for sanitizing or validating the content of the files before processing.
Audit Metadata