Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2025-51482 is a high-severity Code Injection (CWE-94) vulnerability in Letta Letta. 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 22% 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 AI Agent Protocols and Integrations; in the Supply Chain and Deployment 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-2025-51482 is a remote code execution vulnerability in the letta.server.rest_api.routers.v1.tools.run_tool_from_source component of letta-ai Letta version 0.7.12. It affects the /v1/tools/run endpoint and stems from insufficient enforcement of sandbox restrictions, allowing crafted inputs to reach arbitrary Python execution paths classified under CWE-94.
Remote attackers can exploit the flaw over the network without authentication or user interaction by submitting malicious payloads to the endpoint. Successful exploitation grants the ability to run arbitrary Python code and system commands, resulting in full confidentiality, integrity, and availability impact as reflected in the CVSS 8.8 score.
The provided references point to the Letta GitHub repository, a pull request, and an analysis from Gecko Security, but contain no explicit mitigation statements in the supplied data. The EPSS score remains flat at 0.12 with no material increase after disclosure.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-22345
Vulnerability Data
Remote Code Execution in letta.server.rest_api.routers.v1.tools.run_tool_from_source in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai
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.