The Agent Skills Directory

[SAFE]: The skill contains multiple references to dangerous command patterns such as fork bombs (:(){ :|:& };:), reverse shells (nc -e /bin/sh), and destructive commands (rm -rf /). However, these are documented within the rules/dangerous-patterns.md and SKILL.md files as part of a reference library for a security scanning tool. They are data used for pattern matching, not executable code.
[SAFE]: The skill implements a comprehensive safety framework including risk assessment, automated remediation strategies, and structured audit reporting. The rules/anti-aigc.md file specifically enforces high-quality, evidence-based security reporting, which is a defensive measure.
[SAFE]: All functionality described is consistent with its stated purpose as a security review tool for skills. It provides clear guidance for handling dangerous commands, hardcoded credentials, and network requests by recommending standard security practices like environment variables and manual review cycles.

an-jian