Investigate in your agent.

Turn this advisory into a focused investigation. Ask your agent to check your project’s versions, explain the evidence, and suggest a compatible fix.

Your agent needs remote MCP support and access to https://cve.new/mcp.

Read the setup guide

Skip to content
cve.newCreate a CVE report
Check your stack
CVE-2026-119050

Agno through 3.1.11 Code Execution via PandasTools Unsafe Reflection

Products / packages agno-agi agno

Published

Share

Severity and exploitation

Not in CISA KEV

KEV coverage does not rule out exploitation.

KEV checked 07/11/2026, 23:10:32 UTC
VulnCheck · CVSS:4.0 · 9.2
Assessment vectorCVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
VulnCheck · CVSS:3.1 · 8.1
Assessment vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
The headline uses the highest imported catalog score. Assessments can differ by source and CVSS version.

Severity

critical9.2

CVSS measures technical severity, not the likelihood of an attack.

Known exploitation

Not listed in the checked CISA KEV catalog

Absence from CISA KEV does not rule out attacks.

Public exploit

Exploit reference published

Source-linked evidence; not proof of attacks in the wild or independent validation.

Remediation

Fix status not established

No structured fix or guidance is available here. Check the latest publisher advisory.

What this means

Agno through version 3.1.11 has an unsafe reflection vulnerability in PandasTools, allowing attackers to invoke arbitrary pandas functions. Attackers can use prompt injection to call pandas functions like pandas.read_pickle on controlled paths.

Summarized by @cf/meta/llama-3.3-70b-instruct-fp8-fast. Verify details against the original sources.

Attack conditions

No attack-condition excerpt has been identified here. Review the full source description and references for authentication, network access, and configuration requirements.

Review supporting sources →

Affected versions

Check the exact model, release, and any platform requirements against your installation.

agno-agi · VulnCheck

agno

1 range
VulnCheck version evidence

Package identity

pkg:pypi/agnoExplore agno →

Identity supplied by VulnCheck. Version matching requires compatible range evidence.

Compare with this publisher’s ranges. This does not inspect your installation.

affected

0 → through 3.1.11

custom versions

unaffected

unknown

Other versions: unaffected

Automatic dependency matching is unavailable for this record. Use the product evidence and publisher’s instructions to check your installation.

What to do

Compare your installed product and version with the affected versions above. A matching product name alone does not confirm exposure.

No structured fix or remediation guidance is available here. Check the full source description and vendor’s latest advisory for a patch or workaround; do not assume another version is safe.

cve.new guidance unless attributed to a publisher. This page does not inspect your installation.

Public exploit evidence

The sources identify public exploit references. We have not independently tested them; their availability does not establish exploitation in the wild.

agno-agi/agno · issues/8699 ↗Attributed to CISA-ADP

Original source description

Read the full publisher description

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr(). Attackers can use prompt injection to make the agent call pandas.read_pickle on attacker-controlled paths for code execution, or call other readers to read local files.

References

5 sources
agno-agi/agno · issues/8699
Public exploit referenceVulnCheck · CISA-ADP
agno-agi/agno · repository
Source referenceVulnCheck
agno-agi/agno · pandas.py
Source referenceVulnCheck
agno-agi/agno · pandas.py
Source referenceVulnCheck
www.vulncheck.com/advisories/agno-through-3.1.11-code-execution-via-pandastools-unsafe-reflection
Security advisoryVulnCheck

Inside the record

Evidence available

Package identity
Version evidence
Remediation guidance · not supplied
Weakness classification
Additional publishers

Describes the evidence in this view, not whether the product is safe.

Original records

CVE-2026-119050

View the latest unmodified CVE JSON from the official source. It may be newer than this imported page.

cve.new JSON →

Underlying weaknesses

The source’s classification of what caused the vulnerability.

CWE-470 ↗

Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection')

VulnCheck

Related →

Environment requirements

These conditions apply together as specified by the publisher. A matching product name alone does not establish exposure.

VulnCheck · platform conditions

Any condition may hold

Vulnerable product

cpe:2.3:a:agno:agno:*:*:*:*:*:*:*:*

Through (inclusive): 3.1.11

Original applicability statements
[
  {
    "nodes": [
      {
        "operator": "OR",
        "negate": false,
        "cpeMatch": [
          {
            "vulnerable": true,
            "criteria": "cpe:2.3:a:agno:agno:*:*:*:*:*:*:*:*",
            "versionEndIncluding": "3.1.11"
          }
        ]
      }
    ]
  }
]
Contributing organizations · 2
VulnCheck

Assigning organization

2026-10-29
CISA-ADP

Additional data publisher

2026-11-04

Timeline

All times UTC

  1. Advisory published

    Publication date supplied by the source.

  2. Source updated

    Latest modification date supplied by the source.

  3. Last imported by cve.new

    Latest catalog import, not the date we first saw this advisory.

What changed

Follow changes
  1. CVE · CVE-2026-119050

    Observed 2026-11-04T01:29:57.389Z · upstream updated 2026-11-04T01:11:52.909Z

    Prioritization updated

    before

    []

    after

    [
  {
    "source": "CISA-ADP",
    "type": "SSVC",
    "role": "CISA Coordinator",
    "timestamp": "2026-11-04T01:11:30.570498Z",
    "decisions": [
      {
        "name": "Exploitation",
        "value": "poc"
      },
      {
        "name": "Automatable",
        "value": "no"
      },
      {
        "name": "Technical Impact",
        "value": "total"
      }
    ]
  }
]

Large field values are marked as truncated previews. Original source snapshots remain retained.

Showing up to 50 most recent observed changes.