testing-for-json-web-token-vulnerabilities
Warn
Audited by Socket on Mar 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS/HIGH-RISK skill. Its stated purpose is coherent, but that purpose is offensive exploitation of JWT-based authentication systems, which is inappropriate to grant an AI agent without strict oversight. Risk is elevated further by the unpinned personal-repo install for jwt_tool and by sending JWT data through third-party tooling like jwt.io. This is not confirmed malware, but it is a high-risk offensive security skill.
Confidence: 92%Severity: 88%
Audit Metadata