component-vuln-intel
Warn
Audited by Socket on Jul 31, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
该技能不是伪装型窃密器,但它明确把AI代理用于进攻性漏洞情报、PoC检索和资产发现,并要求递归处理大量不受信任外部内容,还会跳转安装/调用其他技能。能力与用途一致,但整体属于高风险 offensive skill,应判为 SUSPICIOUS 而非 BENIGN。
Confidence: 94%Severity: 88%
Audit Metadata