fleet-copilot
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's main risk is autonomy, not credential theft. Its purpose matches a copilot/lock-mode workflow, but it explicitly authorizes sustained agent action and implied PR creation without clear per-action approval, and it depends on an unreviewed local script for control logic.
Confidence: 86%Severity: 72%
Audit Metadata