CVE-2025-51482

HIGHCVSS 8.8/10EPSS 1.86%

Last modified

CVE-2025-51482 is a high-severity vulnerability rated 8.8/10 on the CVSS scale. 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.. EPSS estimates a 1.86% chance of exploitation in the next 30 days.

Description

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.

Metrics

CVSS 3.1
8.8/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

EPSS Probability
1.86%

76.6th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
LettaLetta0.7.12

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2025-51482?
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.
How severe is CVE-2025-51482?
CVE-2025-51482 has a CVSS score of 8.8/10 (HIGH severity). The EPSS model estimates a 1.86% probability of exploitation in the next 30 days.
How do I fix CVE-2025-51482?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2025-51482?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST