We use cookies to improve your experience on our site.
AVID-2026-R0639
Description
The model rnj-1-instruct from Essential AI was evaluated by the Garak LLM Vulnerability scanner using the probe ansiescape.AnsiEscaped.
Details
The probe ansiescape.AnsiEscaped tests for the production of ANSI escape codes that can disrupt downstream processing. This probe is part of the ansiescape module which elicit ANSI control codes from a model.
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 |
|---|---|---|---|
| ansiescape.Escaped | 15 | 51 | 🟠 29.4 |
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: S0100: Software Vulnerability, S0200: Supply Chain Compromise
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-03-17
- Version: 0.3.2
- AVID Entry