Browse / Tool and Agent Misuse / CVE-2026-6604
AgentScope vulnerable to Server-Side Request Forgery
- Class
- Tool and Agent Misuse (filed by a model that read the advisory)
- Technique
- Server-side request forgery
- Also involves
- AI Framework and Platform Flaws
- Affected
- agentscope (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
- EPSS
- 0.3% chance of exploitation in 30 days
How it works, in short
Image and audio URL arguments passed to AgentScope's multimodal tools are fetched server-side without checks, so a model-supplied URL can reach cloud metadata endpoints. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-6604
- https://gist.github.com/YLChen-007/e3e0741b297d8c2ffca59b6350d4c657
- https://github.com/agentscope-ai/agentscope
- https://vuldb.com/submit/792224
- https://vuldb.com/vuln/358239
- https://vuldb.com/vuln/358239/cti
Source: GitHub Advisory Database, used under CC BY 4.0.