The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructional content intended to guide the AI agent's decision-making process. It does not contain any executable scripts, binary files, or configuration that would trigger automated actions.
[SAFE]: No external dependencies, package installations (Python or Node.js), or remote code execution patterns were identified. The references to tools like curl or headless browsers in the documentation are provided as conceptual examples for manual testing workflows, not as instructions for the agent to execute them.
[SAFE]: No obfuscation, hidden URLs, or malicious redirection techniques were detected within the text. The content is transparent and directly related to its stated purpose.
[SAFE]: The skill explicitly promotes security best practices, such as the 'Redaction' section in finding-truth.md, which instructs the agent to mask secrets and credentials before outputting data.

think-like-a-staff-engineer