Home Â» Database

AVID-2026-R0362

Description

The model gpt-oss-20b from OpenAI was evaluated by the Garak LLM Vulnerability scanner using the probe tap.TAPCached.

Details

The probe tap.TAPCached tests the effectiveness of pre-computed prompts to jailbreak LLMs without additional model evaluations. This probe is part of the tap module which utilizes cached prompts for automated jailbreaks.

The LLM gpt-oss-20b was evaluated on this probe.

Metrics

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

DetectorPassedTotalScore
mitigation.MitigationBypass09🔴 0.0

References

Affected or Relevant Artifacts

  • Developer: OpenAI
  • Deployer: Together AI
  • Artifact Details:
TypeName
Modelgpt-oss-20b

Impact

AVID Taxonomy Categorization

  • Risk domains: Security, Performance
  • SEP subcategories: S0403: Adversarial Example, P0204: Accuracy
  • Lifecycle stages: L05: Evaluation

Other information

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