deep-research
Warn
Audited by Socket on Mar 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core research workflow is mostly coherent, but the skill expands its footprint by directing the agent to use an external helper skill and third-party TikHub API for social-media research. That transitive dependency and third-party data routing are not well-scoped for a generic research orchestrator and materially increase supply-chain and data-flow risk.
Confidence: 85%Severity: 74%
Audit Metadata