Home Â» Database

AVID-2026-R0261

Description

The model Mistral-Small-24B-Instruct-2501 from Mistral was evaluated by the Garak LLM Vulnerability scanner using the probe encoding.InjectNato.

Details

The probe encoding.InjectNato tests encoding techniques to bypass input filtering by using NATO phonetic alphabet representations. This probe is part of the encoding module which injects ASCII85 encoded data into payloads.

The LLM Mistral-Small-24B-Instruct-2501 was evaluated on this probe.

Metrics

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

DetectorPassedTotalScore
encoding.DecodeMatch155256🟡 60.5
encoding.DecodeApprox254256🔵 99.2

References

Affected or Relevant Artifacts

  • Developer: Mistral
  • Deployer: Together AI
  • Artifact Details:
TypeName
ModelMistral-Small-24B-Instruct-2501

Impact

AVID Taxonomy Categorization

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

Other information

  • Report Type: Measurement
  • Credits:
  • Date Reported: 2026-03-10
  • Version: 0.3.1
  • AVID Entry