Expired50% confidenceFactExact time
SkillSpector supports two detection modes: local rule-based static scanning that requires no model, and deep semantic analysis that connects to a large language model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
SkillSpector: NVIDIA's Open-Source Security Scanner for AI Agent Skills
bilibiliAIlazy俊6/19/2026
Related Claims
UnverifiedMonocular solutions are better suited as screening tools to quickly identify problematic road sections for follow-up verification by professional equipment, rather than as direct replacements for high-precision measurement.73% similarUnverifiedThe candidate's team used an internal platform based on DeepSeek's underlying model to generate test cases, employing the Harness framework and using Skills and Rules to constrain the large model's output.71% similarUnverified同一个模型用同一套假设检查自己的代码天然看不到盲点，跨模型审查因训练侧重点不同才具备互补价值71% similarUnverifiedThe benchmark adopts a fully automated dual-dimension evaluation approach, covering a functional testing dimension and a visual fidelity dimension.71% similarUnverified评测角色LoRA时应使用复杂提示词检验模型在全新场景中的泛化能力，而非仅测试记忆能力70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41755API
curl https://kongchang.com/api/v1/knowledge/claims/41755MCP
get_claim(id=41755)