CVE Feed

    Dashboard / CVE / CVE-2026-5970

    CVE-2026-5970

    A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.

    Published:Apr 9, 2026
    Last Modified:Apr 29, 2026
    EPS:Apr 9, 2026
    EPSS Score:0.00068
    CVSS Score:7.3

    Affected Products

    Vendor
    Deepwisdom
    Product
    Metagpt
    Vendor
    Foundation Agents
    Product
    Metagpt

    Exploits

    https://github.com/FoundationAgents/MetaGPT/issues/1942https://vuldb.com/submit/791693

    Common Attack Pattern Enumeration and Classification (CAPEC)

    CAPEC-10 Buffer Overflow via Environment Variables
    CAPEC-101 Server Side Include (SSI) Injection
    CAPEC-105 HTTP Request Splitting
    CAPEC-108 Command Line Execution through SQL Injection
    CAPEC-120 Double Encoding
    CAPEC-13 Subverting Environment Variable Values
    CAPEC-135 Format String Injection
    CAPEC-14 Client-side Injection-induced Buffer Overflow
    CAPEC-24 Filter Failure through Buffer Overflow
    CAPEC-242 Code Injection
    CAPEC-250 XML Injection
    CAPEC-267 Leverage Alternate Encoding
    CAPEC-273 HTTP Response Smuggling
    CAPEC-28 Fuzzing
    CAPEC-3 Using Leading 'Ghost' Character Sequences to Bypass Input Filters
    CAPEC-34 HTTP Response Splitting
    CAPEC-35 Leverage Executable Code in Non-Executable Files
    CAPEC-42 MIME Conversion
    CAPEC-43 Exploiting Multiple Input Interpretation Layers
    CAPEC-45 Buffer Overflow via Symbolic Links
    CAPEC-46 Overflow Variables and Tags
    CAPEC-47 Buffer Overflow via Parameter Expansion
    CAPEC-51 Poison Web Service Registry
    CAPEC-52 Embedding NULL Bytes
    CAPEC-53 Postfix, Null Terminate, and Backslash
    CAPEC-6 Argument Injection
    CAPEC-64 Using Slashes and URL Encoding Combined to Bypass Validation Logic
    CAPEC-67 String Format Overflow in syslog()
    CAPEC-7 Blind SQL Injection
    CAPEC-71 Using Unicode Encoding to Bypass Validation Logic
    CAPEC-72 URL Encoding
    CAPEC-76 Manipulating Web Input to File System Calls
    CAPEC-77 Manipulating User-Controlled Variables
    CAPEC-78 Using Escaped Slashes in Alternate Encoding
    CAPEC-79 Using Slashes in Alternate Encoding
    CAPEC-8 Buffer Overflow in an API Call
    CAPEC-80 Using UTF-8 Encoding to Bypass Validation Logic
    CAPEC-83 XPath Injection
    CAPEC-84 XQuery Injection
    CAPEC-9 Buffer Overflow in Local Command-Line Utilities

    Related CVEs

    CVE-2026-6111 (CVSS 2.1) — A security flaw has been discovered in FoundationAgents MetaGPT up to 0.8.1. This impacts the function decode_…
    CVE-2026-6110 (CVSS 5.5) — A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generate_tho…
    CVE-2026-6109 (CVSS 2.1) — A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The impacted element is the function e…
    CVE-2026-5974 (CVSS 6.9) — A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The affected element is the function B…
    CVE-2026-5973 (CVSS 5.5) — A vulnerability was found in FoundationAgents MetaGPT up to 0.8.1. Impacted is the function get_mime_type of t…
    CVE-2026-5972 (CVSS 5.5) — A vulnerability has been found in FoundationAgents MetaGPT up to 0.8.1. This issue affects the function Termin…
    CVE-2026-5971 (CVSS 5.5) — A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionN…
    CVE-2026-4516 (CVSS 2.1) — A vulnerability was found in Foundation Agents MetaGPT up to 0.8.1. This vulnerability affects unknown code of…
    CVE-2026-4515 (CVSS 2.1) — A vulnerability has been found in Foundation Agents MetaGPT up to 0.8.1. This affects the function code_genera…
    CVE-2026-0761 (CVSS 9.8) — Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This…

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High