The Agent Skills Directory

[SAFE]: The skill's primary function is to enhance security by identifying exposed PII and secrets. It uses standard tools like grep and provides clear, non-obfuscated Python and JavaScript scripts for local execution.
[PROMPT_INJECTION]: The skill is designed to ingest and process external data from files and logs, which presents an attack surface for indirect prompt injection. Ingestion points: PIIDetector.scan_file (Python) and scanFile (JavaScript) functions; Boundary markers: Absent; Capability inventory: Read, Write, and Bash tools; Sanitization: The skill implements mask_pii / maskPII functions to redact sensitive values in generated reports, mitigating the risk of full data exposure.

pii-detector