The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform various shell-based operations for project optimization and analysis.
Dependency management commands using npm and npx, including npm install sharp, npm uninstall moment, and npm install date-fns.
Performance auditing via the lighthouse CLI targeting external URLs.
Bundle analysis using npx webpack-bundle-analyzer on local JSON statistics files.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from potentially untrusted external sources, creating a vulnerability surface.
Ingestion points: The agent is instructed to run performance audits on arbitrary URLs and analyze build metadata files (dist/stats.json) provided by the user or project environment.
Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded prompts within the content of analyzed websites or metadata files.
Capability inventory: The skill has access to shell command execution (npm, npx, lighthouse) and the ability to generate and execute Node.js scripts (e.g., the optimize-images.js example) on the local filesystem.
Sanitization: There are no documented procedures for sanitizing the output of performance tools or the content of external files before the agent processes them.

web-performance-optimization