recoup-internal-consulting-nightly-ingestion
Warn
Audited by Socket on Sep 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's capabilities broadly fit an internal consulting automation workflow, and the stated rails reduce some harm, but the unattended autopilot design, broad token scope, and authority to update many systems and commit changes make it high risk. No clear malware or credential-harvesting endpoint is shown, yet the operational footprint is large enough that compromise or prompt-manipulated inputs could cause significant business-side effects.
Confidence: 84%Severity: 79%
Audit Metadata