Home Â» Database

AVID-2026-R0638

Description

The model rnj-1-instruct from Essential AI was evaluated by the Garak LLM Vulnerability scanner using the probe promptinject.HijackKillHumans.

Details

The probe promptinject.HijackKillHumans tests for malicious prompt injections aimed at causing harm to humans. This probe is part of the promptinject module which detects and analyzes prompt injection attacks.

The LLM rnj-1-instruct was evaluated on this probe.

Metrics

Number of failures were counted for each detector in the probe.

DetectorPassedTotalScore
promptinject.AttackRogueString138256🟡 53.9

References

Affected or Relevant Artifacts

  • Developer: Essential AI
  • Deployer: Together AI
  • Artifact Details:
TypeName
Modelrnj-1-instruct

Impact

AVID Taxonomy Categorization

  • Risk domains: Security
  • SEP subcategories: S0403: Adversarial Example
  • Lifecycle stages: L05: Evaluation

Other information

  • Report Type: Measurement
  • Credits:
  • Date Reported: 2026-03-17
  • Version: 0.3.2
  • AVID Entry