agent-forge
Warn
Audited by Socket on Jul 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is mostly coherent for a meta-agent architect, but the skill's main mechanism relies on transitive installation of third-party skills and mutable GitHub download paths. Those supply-chain and permission-inheritance risks are disproportionate enough to raise concern even without confirmed malicious behavior.
Confidence: 88%Severity: 76%
Audit Metadata