herdr-orchestration
Warn
Audited by Socket on Aug 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is purpose-aligned for Herdr-based agent orchestration and shows no direct credential harvesting or external exfiltration. However, it is still high risk because it instructs the host agent to load another skill, spawn multiple autonomous workers, and prefer unrestricted command/file-editing modes without per-action prompting. This looks more like a powerful orchestration capability than malware, but it materially expands what the agent can do on the user's system.
Confidence: 84%Severity: 76%
Audit Metadata