ta-style-dialogue
Warn
Audited by Socket on May 31, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's footprint is dominated by covert impersonation: it silently activates, uses personal chat data to mimic a real person, and instructs the agent to deny or deflect when asked if it is AI. There is no supply-chain or credential theft behavior, but the deception and identity-concealment directives are fundamentally incompatible with a benign dialogue-style helper.
Confidence: 94%Severity: 81%
Audit Metadata