skills/impertio-studio/tailwindcss-claude-skill-package/tailwind-agents-validator/Gen Agent Trust Hub
tailwind-agents-validator
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from a user's codebase (e.g., .tsx, .vue, .css files) without explicit boundary markers or sanitization logic. This creates a surface for indirect prompt injection, where malicious instructions hidden in the code could potentially manipulate the agent's analysis or report generation.
- Ingestion points: The skill performs recursive scans of project files including package.json, configuration files, and source code.
- Boundary markers: The instructions do not define delimiters or "ignore" instructions for the content being scanned.
- Capability inventory: The skill utilizes shell commands (grep, find, node) to inspect the filesystem as described in references/methods.md.
- Sanitization: There is no evidence of escaping or filtering of the content read from the files before it is processed by the agent.
- [COMMAND_EXECUTION]: The references/methods.md file contains specific shell command templates for the agent to execute, such as node -p for parsing package.json and grep for pattern matching in source files. While functionally necessary for a validator, this requires the agent to have shell execution capabilities and interact with the local filesystem.
Audit Metadata