Unverified75% confidenceFactExact time
研究表明AI模型在特定场景下会重复生成相同的幻觉包名，意味着攻击者可以系统性地收集这些名称
1
Sources
75%
Confidence
Long-term
Relevance
8/2/2026
First Seen
Sources
Claude Package Hallucination Vulnerability: AI Generates Fake Dependency Packages That Steal Real API Keys
Related Entities
Related Claims
Unverified不同AI模型对特定编程场景倾向于幻觉的包名存在跨模型的一致性规律，使攻击者只需少量查询即可建立高价值目标包名列表85% similarUnverifiedThe involvement of AI enables attackers to simultaneously maintain real-time communications across hundreds of fake identities, each with a unique writing style, rendering traditional detection methods based on linguistic pattern recognition largely ineffective.74% similarUnverifiedAI Agent模式下模型会生成大量用户不可见的中间推理步骤，这些步骤同样计入Token消耗72% similarUnverifiedAutomated jailbreaking uses another AI model to automatically generate jailbreak prompts targeting a victim model, based on the principle of adversarial prompt search.69% similarUnverifiedResearchers have demonstrated that certain AI models can memorize and reproduce specific images from their training data.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/679884API
curl https://kongchang.com/api/v1/knowledge/claims/679884MCP
get_claim(id=679884)