pentest-conventions
Warn
Audited by Socket on Oct 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent as a pentesting convention guide, but it enables offensive security operations and direct tool execution by an AI agent. There is no clear credential theft or exfiltration behavior, so it is not malicious, but the capability itself is high risk and only partially constrained by a local scope file.
Confidence: 86%Severity: 78%
Audit Metadata