Unverified50% confidenceBenchmarkExact time
Test data provided by the author of GuardAgent-OS shows a containment rate of 99.4% against common prompt injection attacks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedAccording 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.71% similarUnverifiedResearch indicates that an attacker needs to modify as little as 0.01% of training data to potentially implant backdoor behaviors in a model that are undetectable by standard evaluations.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70% similarUnverifieddeepset-deberta and fmops-distilbert captured 100% of attacks in the tests, but their false positive rate was as high as 98%.69% similarUnverifiedIn tests with 629 AgentDojo attacks and 97 benign tool outputs, jailbreak-detector-large achieved a capture rate of 51% with a false positive rate of 2%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043844API
curl https://kongchang.com/api/v1/knowledge/claims/1043844MCP
get_claim(id=1043844)