warden-sweep
Warn
Audited by Socket on Apr 28, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
The skill is purpose-aligned for automated codebase review, but it is high-impact automation: it scans all repo content, invokes subagents on untrusted code, edits files, pushes branches, and opens GitHub PRs/issues. No clear exfiltration or credential-harvesting behavior is described, so this is not malware, but it is a medium-high risk skill that should be treated as sensitive automation.
Confidence: 83%Severity: 68%
Audit Metadata