Unverified50% confidenceFactExact time
According 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedGoogle says Argon leads on the Gray Swan indirect prompt injection benchmark, with an attack success rate of 0.7% across 15 adaptive attempts.70% similarUnverifiedIn the Google FRAMES benchmark, a simple agent loop (capable of reading retrieved results and searching again) achieved an accuracy of 92.7%.69% similarUnverifiedIn a controlled experiment in which dangerous commands were mixed in, humans intercepted only 13.6% of the dangerous operations, while the machine classifier intercepted 89%.67% similarUnverifiedUsing only synthetic weak instructions fed directly into the navigator, the success rate was 15.27%, falling between the exhaustive command rate of 31.03% and the real user instruction rate of 11.33%.67% similarUnverifiedAnthropic's research shows that Auto Mode successfully intercepts dangerous commands at a rate as high as 80%, while human review has a success rate of only 13.6%.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1020745API
curl https://kongchang.com/api/v1/knowledge/claims/1020745MCP
get_claim(id=1020745)