pentestcompanion-workspace
Warn
Audited by Socket on Sep 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is coherent with a pentest workspace and most data flows are proportionate to that purpose, but it materially elevates risk by giving an AI agent offensive-security workflow capabilities and by sourcing the software from an unrelated personal GitHub repo rather than a clearly verified publisher channel. No direct credential theft, hidden exfiltration, or malicious pre-execution behavior is shown in the provided skill text.
Confidence: 87%Severity: 74%
Audit Metadata