skills-discovery
Warn
Audited by Socket on Jul 31, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose mostly matches its behavior, and data flows remain local, but it relies on several unverifiable local CLIs/hooks that gate agent behavior machine-wide. The main risk is install/execution trust and broad enforcement scope, not confirmed malware or credential theft.
Confidence: 86%Severity: 72%
Audit Metadata