hunt-race-condition
Warn
Audited by Socket on Sep 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s content is internally consistent with its stated purpose, but that purpose is to give an AI agent offensive race-condition exploitation capability. Install trust is relatively normal because it mainly references official tools and registries, and there is no clear credential exfiltration or malicious installer chain. However, the capability itself is high risk for AI-agent use because it enables active attacks on external systems, including rate-limit bypass, double-spend, OTP/MFA races, and account-flow exploitation.
Confidence: 89%Severity: 82%
Audit Metadata