plan-review
Warn
Audited by Socket on Jun 30, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the stated purpose is coherent, but the implementation relies on external agent CLIs and explicitly uses approval-bypass/autonomous flags that are excessive for plan review. Data flows to third-party tools are expected for review, yet trust is uneven across the referenced CLIs and the generic `agent` command is especially unclear.
Confidence: 82%Severity: 62%
Audit Metadata