Unverified60% confidenceCautionExact time
Directly 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.
2
Sources
60%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
Harness架构实战：企业级Agent项目全解析
Related Claims
UnverifiedUsing Skill files packaged by others carries security risks and may introduce malicious instructions.81% similarVerifiedThe core security risks of computer use capability include prompt injection attacks and unauthorized access to sensitive local data.78% similarUnverified组合多个各自安全的技能模块可能产生意料之外的安全缺口，例如文件读取技能与网络通信技能结合可被利用实现数据外泄78% similarVerifiedOpenClaw carries security risks: because its built-in tools have extremely high permissions (capable of operating system files, reading browser information, and executing tasks online), any configured API Keys are highly susceptible to leakage if the machine is compromised.77% similarUnverifiedRunning unknown code in a high-privilege (root) environment carries security risks and requires careful operation.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503860API
curl https://kongchang.com/api/v1/knowledge/claims/503860MCP
get_claim(id=503860)