Unverified50% confidenceCautionExact time
涉及代码执行的任务中某些异常信息（如动态代码求值报错）可能被安全系统误读为威胁信号
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
AI误判封号事件：Excel任务触发安全警报的深层警示
Related Claims
Partially VerifiedIndirect prompt injection attacks plant hidden instructions within normal business data to induce Agents into executing unauthorized operations, representing a security risk at the semantic level rather than the code level.79% 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.74% similarUnverified允许AI会话互相发消息带来安全风险，恶意构造的消息可能导致目标会话执行危险命令，如删除文件或泄露敏感信息73% similarUnverified面对运行时动态加载的恶意代码，代码审查和静态扫描等传统安全手段几乎完全失效73% similarUnverified在具备工具调用能力的 Agentic 系统中，一次成功的提示注入可能导致数据泄露、恶意代码执行甚至供应链攻击72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/504199API
curl https://kongchang.com/api/v1/knowledge/claims/504199MCP
get_claim(id=504199)