The Agent Skills Directory

[COMMAND_EXECUTION]: Employs standard system utilities like grep, find, and git, along with the npm package manager, to analyze the project's source code and configuration.
[DATA_EXPOSURE]: Specifically targets the identification of hardcoded secrets, API keys, and sensitive files (e.g., .env) to report them to the user for remediation; no evidence of external exfiltration was found.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing untrusted project files. 1. Ingestion points: grep, cat, and find operations across application source files. 2. Boundary markers: None. 3. Capability inventory: Execution of diagnostic shell commands. 4. Sanitization: None.

security-check