Unverified50% confidenceEventExact time
The National Ministry of Industry and Information Technology Emergency Center once issued a security risk alert pointing out that certain open-source intelligent agents contain a large number of built-in security vulnerabilities.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe Ministry of Industry and Information Technology issued a security warning regarding a type of AI Agent tool, listing multiple vulnerabilities.77% similarUnverifiedPrompt injection has become one of the most closely watched attack surfaces in the field of agent security75% similarUnverifiedMultiple security studies in 2024 confirmed that mainstream tools including GitHub Copilot exhibit varying degrees of indirect prompt injection vulnerabilities.72% similarUnverifiedDirectly executing Skill code downloaded from the internet or autonomously generated by an agent in the host environment poses security risks, as it may contain dangerous operations such as deleting files, accessing sensitive directories, or launching network attacks.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/905969API
curl https://kongchang.com/api/v1/knowledge/claims/905969MCP
get_claim(id=905969)