ce-plan
Warn
Audited by Socket on Mar 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The core planning behavior is coherent and mostly benign, but the skill reaches beyond pure planning by enabling third-party content upload, transitive skill loading, and issue/workflow execution. The biggest concern is optional exfiltration of full plan contents to proofeditor.ai and the added trust chain from loading other skills; these make the footprint broader than a simple planning helper.
Confidence: 84%Severity: 57%
Audit Metadata