The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands including npm run build, npm install, grep, and find to perform project analysis and dependency management. These are routine actions for performance auditing and do not exhibit malicious intent.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from local project files which could theoretically contain malicious instructions. 1. Ingestion points: Reads source code and configuration files via grep and find. 2. Boundary markers: Absent. 3. Capability inventory: Executes shell commands, runs build scripts, and modifies dependencies. 4. Sanitization: No specific validation of ingested content is performed.

performance-audit