MediumVulnerabilityLLM-specific
CVE-2026-85703: freegpt-webui resource allocation flaw in Jailbreak Mode getJailbreak
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-85703
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.6%
Summary
A flaw in the getJailbreak function of server/backend.py in ramon-victor freegpt-webui, up to commit 098db3dfeb41555c2ca9269df0f13e10ec1c35dc, can be triggered remotely through its Jailbreak Mode component to cause resource allocation. A public exploit has been published. The product uses a rolling release, so affected version information is unavailable, and the source says the issue only affects products no longer supported by the maintainer.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSimilar attack · The Hacker News
- InfoAddition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoSafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM ServingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online
- MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research