Unverified50% confidenceFactExact time
There have been real cases of development toolchains being poisoned and then attacking developer keys, and a security check on a single call cannot capture data flows across days and across sessions.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDirectly 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.76% similarUnverified恶意开发者的供应链攻击包括域名近似劫持、工具名称冲突、偏好诱导攻击、工具投毒、跑路服务、跨服务器影子劫持、命令注入等74% similarUnverifiedThe attack in which a server silently changes tool definitions after being trusted is referred to by researchers as Tool Poisoning.73% similarUnverifiedSource code auditing cannot detect the threat of a trusting-trust attack, because the threat resides in the binaries of the build toolchain rather than in the source code.72% similarUnverified发现恶意依赖被安装并不能证明恶意代码真的运行过，命中查询工具应被视为深入调查的理由而非入侵结论72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065429API
curl https://kongchang.com/api/v1/knowledge/claims/1065429MCP
get_claim(id=1065429)