CVE-2026-6604: medium-severity vulnerability in modelscope agentscope
modelscope agentscope Cloud Metadata Endpoint _openai_tools.py openai_audio_to_text server-side request forgery
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
33Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 6.9epss 0.3%
A vulnerability was identified in modelscope agentscope up to 1.0.18. Affected by this issue is the function _parse_url/prepare_image/openai_audio_to_text of the file src/agentscope/tool/_multi_modality/_openai_tools.py of the component Cloud Metadata Endpoint. Such manipulation of the argument image_url/audio_file_url leads to server-side request forgery. The attack may be performed from remote. The exploit is publicly available and might be used. The vendor was contacted early about this disclosure but did not respond in any way.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Affected products
modelscope · agentscopepublic PoCs found — 1
cve_referencegist.github.com/YLChen-007/e3e0741b297d8c2ffca59b6350d4c657unverified⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
Related CVEs — modelscope agentscope
In the same product, most dangerous first.
CVE-2026-6605MEDIUMmodelscope agentscope Internal Service _common.py _get_bytes_from_web_url server-side request forgeryEPSS 0.3%CVE-2026-6603MEDIUMmodelscope agentscope _python.py execute_shell_command code injectionEPSS 0.3%CVE-2026-6606MEDIUMmodelscope agentscope _agent_base.py _process_audio_block server-side request forgeryEPSS 0.3%