The Agent Skills Directory

[SAFE]: The skill processes untrusted code provided as input (code_input) using the vulnerability_detector.py script. The analysis is performed strictly through regular expression matching and does not execute the input code or use it in dangerous sinks like eval(), exec(), or subprocess calls.
[SAFE]: The cve_checker.py tool identifies known vulnerabilities in project dependencies using a simulated internal database. It does not perform remote downloads or execute scripts from external repositories.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the skill's scripts or instructions. The author context and repository metadata are consistent with the claimed functionality.

security-vulnerability-scanner