aris-experiment-bridge
Warn
Audited by Socket on May 6, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the overall workflow matches an experiment-deployment bridge, but its footprint is high-risk for an AI skill. Broad Bash(*) access, arbitrary repo cloning, transitive skill invocation, silent fallback behavior, and autonomous remote GPU actions make the scope disproportionate and capable of costly or unsafe actions even without clear malicious intent.
Confidence: 87%Severity: 81%
Audit Metadata