agent-teams
Warn
Audited by Socket on May 11, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s purpose and capabilities mostly align, and installer provenance appears normal, but it grants a coordinated agent team authority to edit code, run tools, push branches, and create PRs automatically. The main risk is autonomous external action and moderate exposure of repo/config data, not clear malware or credential harvesting.
Confidence: 84%Severity: 68%
Audit Metadata