Skip to content
Noroxi
CVE-2026-4516· NVD / CVE Program· CNA VulDB

Foundation Agents MetaGPT DataInterpreter write_analysis_code.py injection

A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of the file metagpt/actions/di/write_analysis_code.py of the component DataInterpreter. The manipulation results in injection. It is possible to launch the attack remotely. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.

LowCVSS 2.1 · v4.0—No exploit No fix recorded

Noroxi analysis

No Noroxi analysis for this record yet

We don't hand-write analysis for the hundreds of thousands of vulnerabilities in the database; that wouldn't be honest. For notable, high-impact vulnerabilities our team writes the mechanism, detection and remediation steps.

We use this product, ask for help
Published
Mar 21, 2026
Updated
Jun 17, 2026
EPSS
0.4% · 35th percentile
Follow this CVE

Sign in to follow · You’ll be notified if a followed record enters KEV, gets an exploit or is updated.

Report tools

JSON

Action score

8

Monitor

Low priority for now.

CVSS
8 / 40 · 2.1 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.4%

CISA SSVC decision

Exploitation
proof of concept
Automatable
no
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · VulDB
5.3
NVD has not scored this yet; the score shown is the CNA’s.

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Affected systems

VendorProduct
deepwisdommetagpt

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • deepwisdom metagptup to 0.8.1 inclusive

Versions reported by the vendor

Affected version ranges reported by the assigning authority (VulDB). Independent of NVD's CPE analysis and usually ahead of it.

  • Foundation Agents MetaGPT

    • 0.8.0, 0.8.1affected

Other highest-scoring records for the same primary product.

  • CVE-2026-0761Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability
    40Plan
  • CVE-2026-0760Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability
    39Monitor
  • CVE-2024-23750MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell metacharacters to subpr
    35Monitor
  • CVE-2026-5974FoundationAgents MetaGPT terminal.py Bash.run os command injection
    28Monitor
  • CVE-2026-5973FoundationAgents MetaGPT common.py get_mime_type os command injection
    23Monitor
  • CVE-2026-5972FoundationAgents MetaGPT terminal.py Terminal.run_command os command injection
    23Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

No fix version is recorded for this entry. Check the references for vendor advisories.

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

No commit or PR link among the references.

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

  • CVE-2026-597019 days apartFoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection
    22Monitor
  • CVE-2026-611021 days apartFoundationAgents MetaGPT Tree-of-Thought Solver tot.py generate_thoughts code injection
    22Monitor
  • CVE-2026-45150 days apartFoundation Agents MetaGPT operator.py code_generate code injection
    8Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • A low-privileged account is enough.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
Integrity
Availability
Attack vector
Network
Attack complexity
Low
Privileges required
Low
User interaction
None
Scope
X

CVSS vector

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

nvd-secondary

Change log

No changes recorded on tracked fields yet. Score, KEV, exploit maturity and fix status changes appear here.

References

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records