unified-router
Warn
Audited by Socket on Apr 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is plausible, but the skill's actual footprint depends on undocumented bridge commands and a script with no verified official provenance, while granting broad always-on routing and cross-engine artifact access. Official Claude/Qwen tooling appears benign, but the custom wrappers that receive task content, local context, and likely auth state make the overall skill high-risk and internally over-broad for a router.
Confidence: 87%Severity: 83%
Audit Metadata