web3-ai-tools
Warn
Audited by Socket on Apr 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent with its stated purpose, but that purpose is an AI-enabled offensive security toolkit. It enables autonomous pentesting, exploit generation, system prompt extraction, credential attacks, and transitive installation of third-party security skills; combined with mixed-provenance installs and external-content ingestion, this makes it high risk even without clear evidence of credential theft or covert exfiltration.
Confidence: 93%Severity: 89%
Audit Metadata