engagement-memory
Warn
Audited by Socket on Sep 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally coherent as a cross-engagement memory tool, but its stated purpose is to improve recon/weaponize and reporting for offensive security work, which makes it a high-risk security/exploit aid for an AI agent. No external installer, credential theft, or exfiltration path is shown in this excerpt, so this is not confirmed malware; the main risk is enabling offensive operations and spreading tactics across engagements via local persistence and optional global sharing.
Confidence: 87%Severity: 74%
Audit Metadata