Unverified50% confidenceFactExact time
Before activating any skill, Claugravity runs a static security scan whose check rules reference the NVIDIA Agent Skills guide and can flag risky shell patterns (such as curl commands executed via pipes) as well as API credentials exposed in prompts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedNVIDIA provides a skill security scanner called SkillSpecter, used to scan third-party skills for security risks.72% similarUnverifiedAgentScope's tool review mechanism classifies tools by risk level, and the system automatically performs security checks when sensitive tools are invoked.70% similarUnverifiedSkills Scan通过静态分析技能模块权限声明、动态监测运行时行为、检测技能间危险交互模式来识别组合性安全隐患70% similarUnverified掌握抓包能力是功能测试和接口测试的分水岭68% similarUnverifiedGuards sit between the model and the tool functions, bearing responsibility for safety validation by checking before any tool is called, and are a key mechanism for defending against prompt injection and abnormal operations.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070525API
curl https://kongchang.com/api/v1/knowledge/claims/1070525MCP
get_claim(id=1070525)