The Agent Skills Directory

[SAFE]: The skill is a pure prompt-based advisor. It contains no executable scripts, shell commands, or external dependencies. All logic is contained within the markdown instructions and reference files.
[SAFE]: No data exfiltration or credential harvesting patterns were detected. The skill does not request access to environment variables, SSH keys, or cloud credentials.
[SAFE]: The skill uses an 'adversarial lens' (Mr. Hyde) for strategic red-teaming of business plans, but this is a conceptual framework for analysis and does not involve bypassing AI safety filters or performing malicious injections.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation attempts were found. The skill correctly identifies its own limitations and routes technical tasks like security audits or code reviews to other specialized tools.

jekyll-hyde