Letta - RCE (CVE-2025-51482)
176Exploiting IPs reported
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.
CrowdSec analysis
CVE-2025-51482 is a remote code execution vulnerability in letta-ai Letta 0.7.12, specifically within the /v1/tools/run endpoint, that allows attackers to execute arbitrary Python code and system commands by sending crafted payloads. This flaw enables threat actors to bypass intended sandbox restrictions, potentially leading to full system compromise and unauthorized access to sensitive data.
CrowdSec has been tracking this vulnerability and its exploits since 10th of September 2025.
Data from the CrowdSec community indicates that exploitation of CVE-2025-51482 is highly selective and intelligence-driven. Threat actors use advanced reconnaissance and carefully choose their targets, often as part of sophisticated campaigns or advanced persistent threat operations. CrowdSec network telemetry also shows that exploitation of CVE-2025-51482 has significantly declined over the past week. Attack volumes are well below the long-term average, suggesting attackers are rapidly losing interest. The vulnerability appears to be falling out of active use across most threat landscapes.
Attackers exploit this vulnerability by sending crafted POST requests to the /v1/tools/run endpoint with a JSON payload containing malicious Python code in the source_code field, enabling remote command execution on the target server.
Exploitation
Get real-time information about exploitation attempts and actors involved.
Common Weakness Enumeration (CWE)
Protection
Find out relevant information to protect your stack against this CVE.
Blocklist
With our advanced worldwide network detection, CrowdSec can provide a list of IPs known for exploiting the vulnerability.
To increase your protection against this CVE, block exploitation attempts with this list of identified actors.