meeting-brief
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is broadly coherent with its stated purpose, but its footprint is expansive: it autonomously reads calendar data, performs deep external research, builds local people dossiers, and sends results through Gmail and optional Slack. No strong evidence of malware or deceptive exfiltration, but the privacy scope, third-party CLI trust, and unattended outbound messaging make it medium-to-high risk for an AI skill.
Confidence: 87%Severity: 66%
Audit Metadata