penetration-test-planner
Warn
Audited by Socket on Sep 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill's offensive-security purpose makes it inherently high risk for an AI agent, and the unrestricted Bash/read/write permissions are broader than a planning-only skill needs. There is no direct malware behavior, credential harvesting, or suspicious installer, but the capability footprint enables real penetration-testing actions with minimal guardrails.
Confidence: 89%Severity: 78%
Audit Metadata