SingGuard-NSFA: Open-source guardrails for agentic AI

SingGuard-NSFA, an open-source guardrail framework for agentic AI, has been released to address operational threats in agent workflows. The framework includes four models ranging from 0.8B to 9B parameters, built on Qwen3.5 base backbones, and defines 185 risk variants organized under the CIA triad of confidentiality, integrity, and availability.

SingGuard-NSFA is an open-source guardrail framework aimed at operational threats in agent workflows. Four models ship at 0.8B, 2B, 4B, and 9B parameters, all built on Qwen3.5 base backbones. Risk taxonomy The NSFA risk taxonomy organizes threats along the CIA triad of confidentiality, integrity, and availability. It defines 185 risk variants grouped under a smaller set of top-level domains and mid-level categories, cross-validated against three OWASP guidelines. Five top-level domains cover query-side threats: prompt injection … More https://www.helpnetsecurity.com/2026/07/15/singguard-nsfa-open-source-agentic-ai-guardrails/ The post SingGuard-NSFA: Open-source guardrails for agentic AI https://www.helpnetsecurity.com/2026/07/15/singguard-nsfa-open-source-agentic-ai-guardrails/ appeared first on Help Net Security https://www.helpnetsecurity.com .