The Agent Skills Directory

[SAFE]: The skill serves as a comprehensive set of guidelines and templates for senior-level software engineering collaboration. It focuses on transparency, craftsmanship, and systematic problem-solving.
[SAFE]: A static detection for destructive system commands (rm -rf /) in references/domains/security.md was evaluated and found to be benign. The string appears within an educational context illustrating how command injection vulnerabilities occur, not as an instruction for the agent to execute.
[SAFE]: No obfuscation techniques, hidden payloads, or suspicious Base64/Unicode patterns were detected across the skill's files.
[SAFE]: The skill explicitly instructs against common security pitfalls, such as hardcoding secrets, skipping input validation, and failing to handle errors gracefully.
[SAFE]: There are no attempts to exfiltrate data, perform unauthorized network requests, or establish persistence. The examples provided (e.g., API calls) are standard development templates.

vibe-coding