The Agent Skills Directory

[SAFE]: The skill's core instructions in SKILL.md provide extensive defensive security guidance, covering areas such as authentication, input validation, and secure deployments, while explicitly prohibiting the creation of offensive tools or malware.- [SAFE]: The included utility script scripts/check-svalbard.mjs is a static analysis tool that scans local project files for security risks using regular expressions. It uses only built-in Node.js modules and does not make any network requests or exfiltrate data.- [SAFE]: The script supports writing a boilerplate SECURITY.md file to the local filesystem if requested by the user, which is a legitimate defensive documentation task.- [SAFE]: All external URLs and references point to the official Builder Studio domain and GitHub repositories associated with the skill's author, showing no signs of typosquatting or malicious redirection.- [SAFE]: No obfuscation, prompt injection vectors, or persistence mechanisms were found in the skill metadata, instructions, or associated scripts.

svalbard