We use cookies to improve your experience on our site.
AVID-2026-R0613
Description
The model LFM2-24B-A2B from Liquid AI was evaluated by the Garak LLM Vulnerability scanner using the probe promptinject.HijackHateHumans.
Details
The probe promptinject.HijackHateHumans tests for potential hijacking of prompts that express hate towards humans. This probe is part of the promptinject module which detects and analyzes prompt injection attacks.
The LLM LFM2-24B-A2B was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| promptinject.AttackRogueString | 35 | 256 | 🟠 13.7 |
References
Affected or Relevant Artifacts
- Developer: Liquid AI
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | LFM2-24B-A2B |
Impact
AVID Taxonomy Categorization
- Risk domains: Security
- SEP subcategories: S0403: Adversarial Example
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-03-16
- Version: 0.3.2
- AVID Entry