CVE-2026-6604 json
modelscope agentscope Cloud Metadata Endpoint _openai_tools.py openai_audio_to_text server-side request forgery
published 2026-04-20 6 mo ago modified 2026-10-26 13 d ago also GHSA-659x-hm75-hpv7 , PYSEC-2026-2329 , EUVD-2026-23773
- cvss
- 7.3
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.3%
- EPSS 0.3% chance of exploitation in 30 days, percentile 21%
- public exploits
- 0
- none known
Summary
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.
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 6 mo ago
Exploit prediction
0.28% chance of exploitation in the next 30 days, higher than 21% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- gist.github.com https://gist.github.com/YLChen-007/e3e0741b297d8c2ffca59b6350d4c657 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 6.9 | 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 |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 3.0 | 7.3 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L/E:P/RL:X/RC:R |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P/E:POC/RL:ND/RC:UR |
| CNA | 4.0 | 5.5 | 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/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| CNA | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| CNA | 2.0 | 7.5 | AV:N/AC:L/Au:N/C:P/I:P/A:P |
| OSV | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
| GitHub | 3.1 | 7.3 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | agentscope | <=1.0.18 |
no fix listed |
Affected products
- modelscope agentscope
Classification
- Weakness
-
- CWE-918 Server-Side Request Forgery
References
-
gist.github.com
/YLChen-007/e3e0741b297d8c2ffca59b6350d4c657
exploit, web
-
vuldb.com
/vuln/358239
vdb-entry, technical-description, web
-
vuldb.com
/vuln/358239/cti
signature, permissions-required, web
-
vuldb.com
/submit/792224
third-party-advisory, web
-
nvd.nist.gov
/vuln/detail/CVE-2026-6604
advisory
-
github.com
/agentscope-ai/agentscope
package
-
pypi.org
/project/agentscope
package
-
github.com
/advisories/GHSA-659x-hm75-hpv7
advisory
Sources
- CVE List CVE-2026-6604
- GitHub Advisory GHSA-659x-hm75-hpv7
- NVD CVE-2026-6604
- OSV PYSEC-2026-2329
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.