The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions and metadata intended to guide an AI agent through a privacy audit workflow. It does not contain executable scripts, binaries, or commands that interact with the host system's sensitive resources.
[SAFE]: No network operations, external downloads, or remote code execution patterns were identified. The skill references local documentation paths for framework context, which is standard for specialized agent skills.
[SAFE]: There are no signs of credential harvesting or hardcoded secrets. The 'What to Look For' section contains search patterns (grep) designed to find PII in target source code, not to exfiltrate data from the environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code files provided by the user. While this creates a surface for indirect prompt injection (where instructions hidden in the analyzed code could influence the agent), the skill provides a structured workflow and specific reporting schema which acts as a logical constraint. This risk is inherent to the intended primary purpose of a code auditing skill.

identifying