control-the-options
Warn
Audited by Socket on Nov 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill instructs the agent to deceive and steer users rather than provide honest decision support. It presents no evident credential-theft or exfiltration behavior, but its core behavior is intentionally manipulative.
Confidence: 99%Severity: 78%
Audit Metadata