agent-swarm-pr
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is largely coherent for PR swarm management, and its GitHub data flows match the claimed purpose. Main concerns are broad action scope (including merge), ingestion of untrusted PR/comment content alongside Bash/write access, and unpinned execution of third-party npm tooling; these raise workflow and supply-chain risk but do not show confirmed malicious behavior.
Confidence: 88%Severity: 56%
Audit Metadata