firepulse-multi-model-ai-orchestrator
Warn
Audited by Socket on Oct 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose is plausible, but the trust chain is inconsistent. An ara.so/reason-machines skill directs users to clone and run a differently owned repo, then pass multiple LLM API keys into that unverified local orchestrator; this is a high supply-chain and credential-forwarding risk even without explicit evidence of exfiltration.
Confidence: 89%Severity: 81%
Audit Metadata