css-performance
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill provides instructions for executing shell commands such as
npx lighthouse-ciandnpx webpack-bundle-analyzer. This grants the agent the capability to execute external processes in the user's environment.\n- [PROMPT_INJECTION] (LOW): There is a potential for Indirect Prompt Injection because the skill is designed to ingest and process source files (e.g.,src/**/*.{js,jsx,ts,tsx},index.html) to perform purging and extraction. Malicious content or instructions embedded in these files could influence agent behavior.\n - Ingestion points: Local source and public directory files specified in the configuration snippets within
SKILL.md.\n - Boundary markers: No specific boundary markers or delimiters are provided to the agent to isolate processed data from instructions.\n
- Capability inventory: Shell execution via
npxand file system read access.\n - Sanitization: No sanitization or validation logic for the content of the processed files is described.\n- [EXTERNAL_DOWNLOADS] (SAFE): The skill utilizes
npxto download and run well-known development tools from the npm registry. Per [TRUST-SCOPE-RULE], these standard tools from a trusted registry are considered safe for the download operation itself.
Audit Metadata