broken-authentication
Warn
Audited by Socket on Oct 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent as an offensive web-authentication testing skill and does not show covert exfiltration, hidden installs, or credential forwarding to unrelated third parties. However, it equips the agent to perform brute-force, session capture, MFA bypass, and other exploit actions against targets, which makes it high security risk despite the authorization gate and safety language.
Confidence: 93%Severity: 84%
Audit Metadata