The Agent Skills Directory

[SAFE]: The skill is a set of instructions for an AI agent to perform security reviews. It contains no executable logic or automated tools and adheres to the intended purpose of providing a structured framework for configuration auditing.- [NO_CODE]: The skill consists exclusively of markdown documentation and static code examples. No scripts, binaries, or active components are included that could perform unauthorized actions.- [PROMPT_INJECTION]: No malicious injection patterns or attempts to override safety guardrails were identified. The instructional language is strictly diagnostic and does not attempt to subvert the agent's core safety protocols.- [DATA_EXFILTRATION]: The skill does not contain logic to access sensitive local files or transmit data to external servers. References to environment variables and credentials are restricted to search patterns used for auditing third-party code.- [EXTERNAL_DOWNLOADS]: The skill does not perform any network operations to download external packages, scripts, or configuration files. Links provided are for attribution and licensing documentation.

insecure-defaults