The Agent Skills Directory

[DATA_EXFILTRATION]: The skill directs the agent to scan codebases for sensitive data points including environment variables referencing third-party API keys and payment SDK configurations. Searching for these credentials within files like .env exposes them to the agent context.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests untrusted content from the web and local environment.
Ingestion points: External data via WebFetch and local files via Glob and Grep.
Boundary markers: No delimiters or isolation instructions are provided to help the agent distinguish between instructions and untrusted data.
Capability inventory: The skill possesses Write permissions for file generation and WebFetch for network access.
Sanitization: No sanitization or validation is performed on the ingested content before it is incorporated into generated documents.

privacy-generator