AVID-2026-R0413

Description

OpenAI ChatGPT Content Safety Explicit Image Bypass

Details

Our investigation demonstrated that it is possible to circumvent OpenAI’s guardrails so that their model can generate images of fictitious and real-life persons that can be manipulated into sexualized positions.

References

Mindgard Disclosure
Bypassing Image Safeguards in ChatGPT

Affected or Relevant Artifacts

Developer: OpenAI
Deployer: OpenAI
Artifact Details:

Type	Name
System	ChatGPT

Impact

(none)

Other information

Report Type: Advisory
Credits: Jim Nightingale, Mindgard
Date Reported: 2026-01-28
Version: 0.3.1
AVID Entry