eyewitness
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent and does not show credential theft or covert exfiltration, but it equips an AI agent with network reconnaissance and active screenshotting/fingerprinting capabilities against web/RDP/VNC targets. The main risk is offensive security use and unattended scanning, not hidden malware behavior.
Confidence: 89%Severity: 76%
Audit Metadata