Unverified50% confidenceBenchmarkExact time
In tests by security organizations, the coding Agent Codex had a 90% success rate of being compromised when facing indirect prompt injection attacks.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/28/2026
First Seen
Valid until: 11/11/2026
Sources
DeepSeek V5 Code Leak? It's Actually a Compatibility Test
bilibili阿梨Aria早鸟报10/28/2026
Related Entities
Related Claims
UnverifiedTest data provided by the author of GuardAgent-OS shows a containment rate of 99.4% against common prompt injection attacks.70% similarUnverified卡内基梅隆大学研究显示对抗性图案攻击成功率在受控环境为90%以上，但引入正常视角变化后降至实际部署场景的30%以下69% similarUnverifiedAccording to Google's safety data, unauthorized shortcuts accounted for 2% of coding evaluation attempts, and indirect prompt injection attacks succeeded in 0.7% of 15 adaptive attempts.67% similarUnverifieddeepset-deberta and fmops-distilbert captured 100% of attacks in the tests, but their false positive rate was as high as 98%.65% similarUnverifiedadversa.ai's CodePoisonRAG research planted 85 poisoned samples across three code-generation agents, achieving attack success rates of 0.80 to 0.93.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1109733API
curl https://kongchang.com/api/v1/knowledge/claims/1109733MCP
get_claim(id=1109733)