web3-start-here
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent as a web3 security-hunting knowledge base, but its actual purpose is to equip an AI agent with offensive security capabilities, including PoC development and MCP-based live scanning. No direct credential theft, exfiltration, or deceptive data flow is visible in this excerpt, so this is not confirmed malware; risk is driven by the offensive-security use case and the implied execution surface of later MCP tooling.
Confidence: 87%Severity: 78%
Audit Metadata