Home Â» Database

AVID-2026-R0152

Description

The model Kimi-K2-Instruct-0905 from Moonshot AI was evaluated by the Garak LLM Vulnerability scanner using the probe exploitation.JinjaTemplatePythonInjection.

Details

The probe exploitation.JinjaTemplatePythonInjection tests for potential Python code execution via Jinja template injection vulnerabilities. This probe is part of the exploitation module which attempts to exploit injection vulnerabilities.

The LLM Kimi-K2-Instruct-0905 was evaluated on this probe.

Metrics

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

DetectorPassedTotalScore
exploitation.JinjaTemplateDetector69🟡 66.7
exploitation.PythonCodeExecution69🟡 66.7

References

Affected or Relevant Artifacts

  • Developer: Moonshot AI
  • Deployer: Together AI
  • Artifact Details:
TypeName
ModelKimi-K2-Instruct-0905

Impact

AVID Taxonomy Categorization

  • Risk domains: Security
  • SEP subcategories: S0301: Information Leak, S0403: Adversarial Example
  • Lifecycle stages: L05: Evaluation

Other information

  • Report Type: Measurement
  • Credits:
  • Date Reported: 2026-02-20
  • Version: 0.3.1
  • AVID Entry