OpenHands 操作系统命令注入漏洞

OpenHands is an open-source AI-driven intelligent agent development platform. Version 1.5.0 of OpenHands contains a vulnerability related to operating system command injection. This vulnerability stems from the getgitdiff method, which allows for command injection, potentially enabling...

Command Injection

Overview openhands-ai is an OpenHands: Code Less, Make More Affected versions of this package are vulnerable to Command Injection via the getgitdiff method. An attacker can execute arbitrary commands, read sensitive files, write arbitrary files, establish persistent access, or potentially escape...

GHSA-7H8W-HJ9J-8RJW OpenHands is Vulnerable to Command Injection through its Git Diff Handler

Summary A Command Injection vulnerability exists in the getgitdiff method at openhands/runtime/utils/githandler.py:134. The path parameter from the /api/conversations/conversationid/git/diff API endpoint is passed unsanitized to a shell command, allowing authenticated attackers to execute arbitra...

Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

Static Application Security Testing SAST tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives FPs, imposing a substantial manual triage burden on developers. Recent advances in Large Language Model LLM agents offer a promising...

EUVD-2025-203510

Malicious code in openhands-frontend npm...

Malicious code in openhands-frontend (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3094854e6f43f64c218e6ccdf21f319cff916fef4a412442faccf4b9cd616fe9 The package openhands-frontend was found to contain malicious code. Source: ghsa-malware...

Malicious Package

Overview openhands-frontend is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

MAL-2025-192593 Malicious code in openhands-frontend (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3094854e6f43f64c218e6ccdf21f319cff916fef4a412442faccf4b9cd616fe9 The package openhands-frontend was found to contain malicious code. Source: ghsa-malware...

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Large language model LLM agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored application is automated web vulnerability reproduction, which...