deep-qa
Warn
Audited by Socket on Oct 3, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's QA purpose broadly matches its behavior, but its actual footprint is wider than necessary because it defaults to third-party execution paths (sagaflow) and forwards artifacts plus API keys to a local script targeting arbitrary OpenAI-compatible endpoints. The main concern is install/execution trust and data-flow integrity, not confirmed malware.
Confidence: 88%Severity: 81%
Audit Metadata