Opening SecureFlowTypeSafe AI Jev: Counterfeit Policy Lowers Injection Recall and Tool-Risk Scores
Case summary & sources

AIDEFEND SecureFlow / SecureFlow Case Index

Datadog Security Labs aidefend-sf0096

TypeSafe AI Jev: Counterfeit Policy Lowers Injection Recall and Tool-Risk Scores

  • Autonomous Agents
  • AI Infrastructure
  • Model Evasion & Bypass

Jev is a TypeSafe AI model that returns structured judgments, such as a probability that an input contains prompt injection. Datadog tested what happens when the text being judged includes a counterfeit policy of its own. Across 12,295 samples, the share of attacks that Jev detected fell from 82.90% to 3.88% using its Noul output. In a separate LangChain simulation, a user-editable profile lowered the mean risk score for a proposed file edit from 0.893 to 0.290. The research measured the gate's decisions and did not report a successful unauthorized write.

Mapped threat techniques

  • AML.T0065 LLM Prompt Crafting
  • AML.T0051.000 Direct
  • AML.T0015 Evade AI Model
  • AML.T0051.001 Indirect

Source