Unverified50% confidenceBenchmarkExact time
Meta Prompt Guard 2 (86M) achieved a capture rate of 1% on the 629 attacks at the default threshold, with a false positive rate of 0%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedIn 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%.73% similarUnverifiedPrompt Guard 2 scored 0.999 on human-written injection instructions, but scored between 0.004 and 0.140 on real AgentDojo attacks, all below the default threshold of 0.5.72% similarUnverifiedOpenAI defense factory real-world metrics: dynamic validation reduced the false positive rate to below 1%, attribution assignment accuracy was approximately 90%, and the fix rollback rate was below 1%.62% similarUnverifiedIn the controlled test, the cache hit rate increased from 76.1% to 85.4%.62% similarUnverifiedOpenAI's GPT-6 Astra system card reports a 99.99% defense rate against direct injection, but attackers still achieved an 8.5% success rate in Gray Swan's external indirect injection arena.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022425API
curl https://kongchang.com/api/v1/knowledge/claims/1022425MCP
get_claim(id=1022425)