CVE-2024-45858
Published: 18 September 2024
Summary
CVE-2024-45858 is a high-severity Eval Injection (CWE-95) vulnerability in Hiddenlayer (inferred from references). Its CVSS base score is 7.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Client Execution (T1203); ranked at the 28.4th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Other Platforms; in the Supply Chain and Deployment risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2024-2883
Vulnerability details
An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the…
more
code will be passed to an eval function, causing it to execute on the user's machine.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Other Platforms
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Guardrails AI is an open-source framework/platform for validating and adding guardrails to LLM outputs and applications, fitting under Other Platforms as a higher-level AI tool beyond core ML libraries or NLP-specific tools.
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability enables arbitrary code execution by loading a malicious XML file that injects Python code evaluated via eval(), facilitating client-side exploitation and Python interpreter abuse.
Affected Assets
Mitigating Controls
No mitigating controls mapped yet. The per-CVE control annotator has not reached this CVE.