dbcve.org
Command InjectionWeakness · CWE-77

CVE-2025-8667

MEDIUM · 6.3 CVSS v3.1 Published 2025-08-06
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
69/100
Remediation priority · Elevated
Remotely reachable Zero-click

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 · unedited
A vulnerability, which was classified as critical, was found in SkyworkAI DeepResearchAgent up to 08eb7f8eb9505d0094d75bb97ff7dacc3fa3bbf2. Affected is the function from_code/from_dict/from_mcp of the file src/tools/tools.py. The manipulation leads to os command injection. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. Continious delivery with rolling releases is used by this product. Therefore, no version details of affected nor updated releases are available. 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 confidence

OS command injection vulnerability in SkyworkAI DeepResearchAgent's src/tools/tools.py. The from_code, from_dict, and from_mcp functions accept user-controlled input that gets passed to shell commands without proper sanitization, allowing remote attackers to execute arbitrary OS commands.

MitigationImplement strict input validation and sanitization on all parameters to these functions; replace shell command execution with safe alternatives such as subprocess with shell=False, parameterized functions, or allowlists of permitted values.

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
Low
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
Low
Availability
Low

CVSS:3.1/AV:N/AC:L/PR:L/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 checks

Work through these to decide whether this CVE applies to you.

  1. Locate the DeepResearchAgent installation
    Search for the src/tools/tools.py file in your environment. Common paths include ./DeepResearchAgent/src/tools/tools.py or similar project directories. Use 'find . -name tools.py -path "*/tools/*"' to locate it.
    Affected if The file exists and belongs to SkyworkAI DeepResearchAgent project
  2. Verify the vulnerable functions exist
    Open src/tools/tools.py and search for function definitions: 'def from_code', 'def from_dict', and 'def from_mcp'. Confirm these three functions are present in the file.
    Affected if All three functions (from_code, from_dict, from_mcp) are defined in the file
  3. Inspect shell command execution patterns
    Within the affected functions, search for patterns indicating shell command execution: look for 'subprocess.run', 'subprocess.call', 'subprocess.Popen', 'os.system', 'os.popen' with 'shell=True', or similar constructs that invoke system commands.
    Affected if Shell command execution (shell=True or os.system/os.popen) is used within these functions
  4. Trace user input to shell commands
    Review the function parameters and how they are used. Check if parameters (such as code, command, or dict inputs) are directly concatenated or interpolated into shell command strings without sanitization, validation, or use of shell=False.
    Affected if User-controllable parameters from these functions flow directly into shell commands without sanitization or use of shell=False
  5. Compare your version to any release information
    Check the installed version of SkyworkAI DeepResearchAgent (typically in setup.py, pyproject.toml, or a version.py file). Compare against any official release notes or patches addressing this vulnerability.
    Affected if Your version is older than the patched release or if no patch is available for your version

You are affected if the src/tools/tools.py file contains from_code, from_dict, or from_mcp functions that pass user input to shell commands without sanitization or shell=False.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

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 data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Implement strict input validation and sanitization on all parameters to these functions; replace shell command execution with safe alternatives such as subprocess with shell=False, parameterized functions, or allowlists of permitted values.

Have this fixed Scoped from the published advisory
  • Consultation6.0 h
  • Implementation12.0 h
  • Testing6.0 h
  • Review / QA4.0 h
28.0 hours of engineering $4,980
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,968.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-8667 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2025-8667 in production — separate from our analysis above.

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.

What this is

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.

What belongs here
  • 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