Raw vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2025-0185 is a high-severity Code Injection (CWE-94) vulnerability in Dify Dify. Its CVSS base score is 8.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 40% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; 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.
A vulnerability tracked as CVE-2025-0185 exists in the Dify Tools Vanna module of the langgenius/dify repository. The flaw is a Pandas Query Injection in the function vn.get_training_plan_generic(df_information_schema), which fails to sanitize user inputs before passing them to Pandas query execution and is tracked under CWE-94. The component is exposed in the latest version of the affected repository and carries a CVSS 3.1 score of 8.8.
An authenticated attacker with network access can supply crafted input that results in remote code execution, granting full control over confidentiality, integrity, and availability without user interaction. The attack vector is rated as low complexity under the CVSS metrics.
Public references consist of a huntr.com bounty entry that describes the injection path but provides no explicit patch or mitigation details in the available information. The associated EPSS score has remained low, reaching a peak of only 0.0379.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-6817
Vulnerability Data
A vulnerability in the Dify Tools' Vanna module of the langgenius/dify repository allows for a Pandas Query Injection in the latest version. The vulnerability occurs in the function `vn.get_training_plan_generic(df_information_schema)`, which does not properly sanitize user inputs before executing queries using…
more
the Pandas library. This can potentially lead to Remote Code Execution (RCE) if exploited.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: dify, pandas
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.3.1
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.
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.
Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.