reload
Warn
Audited by Socket on Jul 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent and does not show credential theft or third-party exfiltration, but it enables autonomous future prompt injection into an agent/session via a detached background timer. Supply-chain risk is low-to-medium and mainly inherited from the external Herdr installer, while the main security concern is real-world autonomous action without immediate user oversight.
Confidence: 88%Severity: 72%
Audit Metadata