CVE-2026-6603
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedA vulnerability was determined in modelscope agentscope up to 1.0.18. Affected by this vulnerability is the function execute_python_code/execute_shell_command of the file src/AgentScope/tool/_coding/_python.py. This manipulation causes code injection. The attack is possible to be carried out remotely. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · moderate confidenceCode injection vulnerability in AgentScope's Python tool allows remote attackers to execute arbitrary code through the execute_python_code/execute_shell_command functions in src/AgentScope/tool/_coding/_python.py. The vulnerability stems from insufficient input sanitization before passing user-controlled data to code execution functions.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- Low
- Availability
- Low
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify AgentScope installation and versionRun 'pip show agentscope' or 'pip list | grep agentscope' to find the installed version. If not installed via pip, search for the agentscope directory in your Python environment.Affected if The installed version falls within an unpatched range (any version prior to vendor fix).
-
Locate the vulnerable module fileSearch for the file 'src/AgentScope/tool/_coding/_python.py' in your installation directory. Use 'find /path/to/site-packages -name _python.py -path "*agentscope*"' or check your AgentScope installation path.Affected if The file exists and contains the execute_python_code or execute_shell_command functions, indicating the vulnerable code is present.
-
Inspect the execute_python_code functionOpen the _python.py file and examine the execute_python_code function. Look for input validation or sanitization on the 'code' parameter before execution.Affected if The function directly passes user-controlled input to exec(), eval(), or similar code execution primitives without adequate sanitization.
-
Verify exposure of code execution functionsCheck if execute_python_code or execute_shell_command are exposed through API endpoints, web interfaces, or can be called with untrusted user input. Review your AgentScope deployment configuration and any exposed service interfaces.Affected if These functions are accessible to untrusted users or external systems without proper input validation guards.
You are affected if AgentScope is installed with the vulnerable _python.py module containing unsanitized execute_python_code/execute_shell_command functions that can be invoked with user-controlled input.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
From vendor dataImplement strict input validation and sanitization for all code passed to execute_python_code/execute_shell_command functions. Consider deploying a sandboxed execution environment with restricted permissions and whitelisted allowed operations. Monitor for any patch releases from the vendor.
- Consultation4.0 h
- Implementation12.0 h
- Testing8.0 h
- Review / QA4.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,808.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-6603 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-6603 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data