train-complex-blackbox
Warn
Audited by Socket on May 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the AgentJet dependency path appears coherent and same-org, but the skill’s actual footprint is broad. It asks for API credentials, forwards them into arbitrary agent execution, and optionally performs SSH-based remote orchestration. These behaviors can fit the stated training purpose, yet they create disproportionate credential and command-execution risk for an AI skill.
Confidence: 84%Severity: 72%
Audit Metadata