hunt-oauth
Warn
Audited by Socket on Aug 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
High-risk offensive security skill. Its content is internally consistent with OAuth hunting, but it gives an AI agent concrete instructions to probe targets, craft exploit payloads, and validate account-takeover paths, including token/code capture. There is little evidence of hidden malware or deceptive install behavior, yet the skill materially increases the agent’s ability to perform unauthorized security testing and credential/session theft workflows.
Confidence: 91%Severity: 84%
Audit Metadata