Unverified50% confidenceFactExact time
HelloSquatting攻击利用AI编程助手生成不存在的仓库或技能名称，攻击者提前注册这些名称等待代理拉取恶意资源
1
Sources
50%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
GPT-5.6 Sol Limited Preview: The Safety Boundaries Behind AI's Capability Expansion
bilibili江枫渔火AI7/9/2026
Related Claims
UnverifiedIndirect prompt injection refers to attack instructions hidden in external web pages, documents, or API responses accessed by an agent, where the malicious instructions are activated when the agent retrieves and injects them into the context.69% similarUnverifiedDevTools for Agents让AI代理能够进入真实浏览器环境，观察运行时状态、定位问题并完成修复66% similarVerifiedPrompt injection attacks are a serious threat facing local AI Agents, as maliciously crafted content in files processed by the Agent may induce it to execute dangerous operations.65% similarUnverified攻击者通过提示词注入控制Agent的决策逻辑后，可利用Agent已获授权的所有工具和接口实现全链路攻击，形成混淆代理人（Confused Deputy）问题65% similarUnverifiedUsers can connect their own AI Agents to the Portfolio Lab platform and deploy only Vetted strategies.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487541API
curl https://kongchang.com/api/v1/knowledge/claims/487541MCP
get_claim(id=487541)