CVE-2026-6603: AgentScope Vulnerable to Remote Code Injection
Affects agentscopeSource GCVE Database
Public exploit available · CVSS 6.9 Medium.
Data as of 27 Oct 2026, 00:29 UTC
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:PExploitation evidence
Disclosed: evidence found.
CVE published 20 Apr 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: evidence found.
CVSS exploit maturity: proof of concept public
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| PyPIagentscope | Affected
| Fixed in– |
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Users should consider disabling or restricting access to the vulnerable functions or the AgentScope service until a fix is provided. Monitor for vendor advisories for updates.
Description
AgentScope versions up to 1.0.18 contain a remote code injection vulnerability in the execute_python_code and execute_shell_command functions. This flaw allows an attacker to execute arbitrary code remotely. The vulnerability has a high severity CVSS score of 7.3 and public exploit details have been disclosed. The vendor has not responded or provided a patch.
References
- nvd.nist.gov/vuln/detail/CVE-2026-6603 (opens in a new tab)
- gist.github.com/YLChen-007/c084d69aaeda6729f3988603f2b0ce6e (opens in a new tab)
- github.com/agentscope-ai/agentscope (opens in a new tab)
- vuldb.com/submit/792223 (opens in a new tab)
- vuldb.com/vuln/358238 (opens in a new tab)
- vuldb.com/vuln/358238/cti (opens in a new tab)