css-styling-expert
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute discovery and validation commands. It performs environment detection using
grep,ls, andcat, and executes project-specific build scripts vianpm run buildto verify CSS changes. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto run utility tools such asstylelintandlighthouse. These commands may download packages from the official npm registry if they are not already present in the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from the user's repository to provide styling recommendations.
- Ingestion points: Files are read through the
Read,Grep, andGlobtools, as well as shell commands likecatandgrep. - Boundary markers: The instructions do not specify any delimiters or ignore-instructions warnings for the processed file content.
- Capability inventory: The skill has access to shell execution via
Bashand file modification viaEditandMultiEdit. - Sanitization: There is no explicit sanitization or validation of the file content before it is processed by the agent's logic.
Audit Metadata