html-tailwind-css-and-javascript-expert-rule
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes project files, creating a surface for indirect prompt injection via untrusted code content. * Ingestion points: Processes files matching **/*.{html,js,css}. * Boundary markers: No explicit instructions for handling embedded instructions. * Capability inventory: Accesses Read, Write, Edit, and Bash tools. * Sanitization: No sanitization is performed on ingested content.
- [COMMAND_EXECUTION]: The skill suggests using the 'cat' command to read a local context file (.claude/context/memory/learnings.md), which is a benign use of shell access for maintaining task state.
Audit Metadata