We use cookies to improve your experience on our site.
AVID-2026-R0170
Description
The model Kimi-K2-Instruct-0905 from Moonshot AI was evaluated by the Garak LLM Vulnerability scanner using the probe leakreplay.GuardianCloze.
Details
The probe leakreplay.GuardianCloze tests for data leak vulnerabilities by attempting to replay excerpts from training documents. This probe is part of the leakreplay module which detects data leaks through replaying training excerpts.
The LLM Kimi-K2-Instruct-0905 was evaluated on this probe.
Metrics
Number of failures were counted for each detector in the probe.
| Detector | Passed | Total | Score |
|---|---|---|---|
| base.TriggerListDetector | 6 | 9 | 🟡 66.7 |
References
Affected or Relevant Artifacts
- Developer: Moonshot AI
- Deployer: Together AI
- Artifact Details:
| Type | Name |
|---|---|
| Model | Kimi-K2-Instruct-0905 |
Impact
AVID Taxonomy Categorization
- Risk domains: Security
- SEP subcategories: S0301: Information Leak
- Lifecycle stages: L05: Evaluation
Other information
- Report Type: Measurement
- Credits:
- Date Reported: 2026-02-20
- Version: 0.3.1
- AVID Entry