CVE-2026-5971
Raw vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/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:XSummary
CVE-2026-5971 is a medium-severity Code Injection (CWE-94) vulnerability. Its CVSS base score is 6.9 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique JavaScript (T1059.007); ranked at the 32th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-5971 is a code injection vulnerability stemming from improper neutralization of directives in dynamically evaluated code (CWE-94, CWE-95) in the ActionNode.xml_fill function within the file metagpt/actions/action_node.py of the XML Handler component. It affects FoundationAgents MetaGPT versions up to 0.8.1. The issue was published on 2026-04-09 with a CVSS v3.1 base score of 7.3 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L), indicating high severity due to its network accessibility and lack of prerequisites.
The vulnerability can be exploited remotely by unauthenticated attackers with low complexity, requiring no user interaction or privileges. Successful exploitation allows limited impacts on confidentiality, integrity, and availability, potentially enabling arbitrary code execution through manipulated XML inputs processed by the dynamic evaluation mechanism.
Advisories referenced in GitHub issues #1928 and #1956, along with VulDB entries, indicate the project was notified early via a pull request but has not yet responded or issued patches. No official mitigations or fixes are available as of the latest reports.
Notably, an exploit has been publicly disclosed and may be actively used. MetaGPT, as a multi-agent framework leveraging large language models, introduces AI/ML-specific risks where XML handling flaws could propagate through agent workflows, amplifying potential impacts in automated decision-making systems.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-21004
Vulnerability Data
A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xml_fill of the file metagpt/actions/action_node.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated code.…
more
The attack may be launched remotely. The exploit has been published and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: metagpt
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1V1.3.2
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation finds code paths that accept and execute externally influenced strings.
Input validation directly stops untrusted data from being used to construct executable code without neutralization.
Least privilege limits the damage an injected code fragment can perform once executed.
Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).
PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development can detect eval injection vulnerabilities before deployment.
Secure development life cycle mandates input validation and safe coding practices that directly prevent eval injection.
Application security requirements include rules against dynamic code execution of untrusted input.
Secure architecture principles discourage unsafe dynamic evaluation constructs.
Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.
Separation of environments limits the blast radius if eval injection occurs in non-production.