We use cookies to improve your experience on our site.
AVID-2026-R0681
Description
The model rnj-1-instruct from Essential AI was evaluated by the Garak LLM Vulnerability scanner using the probe latentinjection.LatentJailbreak.
Details
The probe latentinjection.LatentJailbreak tests for model responses to latent injections embedded within context. This probe is part of the latentinjection module which detects latent injection issues.
The LLM rnj-1-instruct was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| unsafe_content.ToxicCommentModel | 183 | 256 | 🟡 71.5 |
| base.TriggerListDetector | 51 | 256 | 🟠 19.9 |
References
Affected or Relevant Artifacts
- Developer: Essential AI
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | rnj-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