dbcve.org
Command InjectionWeakness · CWE-77

CVE-2025-8665

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, has been found in agno-agi agno up to 1.7.5. This issue affects the function MCPTools/MultiMCPTools in the library libs/agno/agno/tools/mcp.py of the component Model Context Protocol Handler. The manipulation of the argument command leads to os command injection. The attack may be initiated remotely. The exploit has been disclosed to the public and may be used. 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 · high confidence

A command injection vulnerability exists in the agno library's Model Context Protocol (MCP) tools handler (mcp.py). The MCPTools/MultiMCPTools functions accept a command argument that is passed directly to the OS without sanitization, allowing remote attackers to inject and execute arbitrary OS commands.

MitigationUpgrade to agno version >1.7.5. Until a patch is available, implement strict input validation on the command argument and refactor to use subprocess with argument lists instead of shell execution to prevent command injection.

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. Identify installed agno library version
    Run 'pip show agno' or 'pip list | grep -i agno' to see the installed version number
    Affected if The installed version is 1.7.5 or lower (versions up to and including 1.7.5 are affected)
  2. Locate the agno mcp.py module file
    Find the installed agno package location (typically in site-packages/agno/) and locate the mcp.py file within it
    Affected if The mcp.py file exists in the agno package directory and contains MCPTools or MultiMCPTools classes
  3. Inspect code using MCPTools or MultiMCPTools
    Search your codebase for imports or usage of 'from agno import MCPTools' or 'from agno import MultiMCPTools', and review where these classes are instantiated
    Affected if Your code instantiates MCPTools or MultiMCPTools with a command parameter that could be user-controlled
  4. Verify command argument handling
    Examine how the command argument is passed to MCPTools/MultiMCPTools in your code - check if it accepts external/user input without validation
    Affected if The command argument accepts unsanitized input from external sources (users, APIs, files) and is passed directly to the MCP tools
  5. Check for subprocess shell execution patterns
    Review the agno mcp.py source code (if accessible) or runtime behavior to determine if commands are executed via shell=True or equivalent shell invocation
    Affected if The underlying execution uses shell=True or string-based command passing rather than argument lists

You are affected if you are running agno version 1.7.5 or lower and your application uses MCPTools or MultiMCPTools with unsanitized command input from external sources.

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.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to agno version >1.7.5. Until a patch is available, implement strict input validation on the command argument and refactor to use subprocess with argument lists instead of shell execution to prevent command injection.

Recommended fix Moderate confidence

Latest version after 1.7.5 (check PyPI or the agno-agi GitHub repository for the most recent release)

  1. 1. Identify the current version of the agno library in use by checking your project dependencies (e.g., pyproject.toml, requirements.txt, or via 'pip show agno')
  2. 2. Upgrade to the latest available version of agno that addresses this vulnerability
  3. 3. Verify the upgrade completed successfully by running 'pip show agno' and confirming the version number
  4. 4. Test that the MCP tools functionality continues to work correctly after the upgrade
  5. 5. If the vendor has not released a patch (they did not respond), consider implementing input validation on the 'command' argument before passing it to MCPTools/MultiMCPTools, or temporarily disable the MCP tools if not essential
Caveat Check release notes for potential breaking changes between 1.7.5 and the target upgrade version

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation4.0 h
  • Testing2.0 h
  • Review / QA2.0 h
11.0 hours of engineering $1,980
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,168.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-8665 — 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-2025-8665 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