EUVD-2025-210474
GHSA-8j86-h8gg-797p
Severity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Network-reachable and unauthenticated, but the description requires the agent to fetch a crafted page, so UI:R rather than the NVD's UI:N; command injection yields full C/I/A on the host.
Primary rating from Vendor (mitre).
CVSS VectorVendor: mitre
Lifecycle Timeline
4DescriptionCVE.org
An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page.
AnalysisAI
Remote command execution in Open Source GPT Researcher v3.3.7 lets attackers run arbitrary OS commands on a victim's machine when the user interacts with a crafted HTML page, exploiting a command injection (CWE-77) weakness. The flaw was reported by MITRE and detailed in ox.security research covering RCE across the AI/MCP ecosystem; no public exploit is identified in CISA KEV, and EPSS probability is low (0.21%). Because GPT Researcher autonomously fetches and processes web content, a malicious page encountered during a research run can drive execution on the host.
Technical ContextAI
GPT Researcher is an open-source autonomous research agent (Python) that crawls, scrapes, and synthesizes web content, often invoking system-level tooling and external processes as part of its pipeline. The root cause is CWE-77 (Improper Neutralization of Special Elements used in a Command), meaning attacker-influenced content (a crafted HTML page ingested by the agent) reaches a command interpreter or shell without adequate sanitization, allowing injected commands to execute. CPE data is uninformative here (cpe:2.3:a:n/a:n/a:*), so the affected component is identified from the vendor repository (assafelovic/gpt-researcher) and the ox.security advisory rather than structured NVD product data. This class of flaw is characteristic of AI agents that pass fetched/tool-derived content into subprocess or shell calls.
RemediationAI
No vendor-released patch version is identified in the provided data at time of analysis; monitor the upstream repository (https://github.com/assafelovic/gpt-researcher) and the ox.security advisory (https://www.ox.security/blog/gpt-researcher-remote-code-execution) for a fixed release beyond 3.3.7 and upgrade as soon as one is published. As compensating controls, run GPT Researcher inside a locked-down sandbox or container with no shell access and a non-privileged user so injected commands cannot reach the host (trade-off: added deployment complexity); restrict or allowlist the URLs/domains the agent is permitted to fetch to keep it away from attacker-controlled pages (trade-off: reduces research coverage); and apply egress network filtering and least-privilege file/system permissions to limit post-exploitation impact. Avoid pointing the agent at untrusted or user-supplied URLs until a patched version is confirmed.
LibreNMS before 24.10.0 allows a remote attacker to execute arbitrary code via OS command injection involving AboutContr
Reachable assertion in Open5GS up to version 2.7.6 allows remote unauthenticated attackers to crash the Diameter CER han
A Command Injection issue in the payload build page in BYOB (Build Your Own Botnet) 2.0 allows attackers to execute arbi
Denial of service in Open5GS 2.7.6 and earlier allows network-adjacent attackers with low-privilege Diameter Gx peer acc
Denial of service in Open5GS HSS (Home Subscriber Server) versions 2.7.0 through 2.7.6 is triggered remotely by manipula
Remote command injection in Control Web Panel allows unauthenticated attackers to execute arbitrary OS commands as root
LINQPad before 5.52.01 Pro edition is vulnerable to Unsafe Deserialization in LINQPad.AutoRefManager::PopulateFromCache(
Remote code execution in dash-uploader (Python package for Plotly Dash) versions 0.1.0 through 0.7.0a2 allows unauthenti
Command injection in LiteLLM 1.18.10 lets attackers who can configure MCP (Model Context Protocol) servers supply arbitr
SQL injection in AzuraCast's backup restore flow (versions up to and including 0.23.7) lets an attacker achieve privileg
Arbitrary file read in Yu AI Code Mother v4.3 lets anonymous, remote attackers retrieve files outside the intended previ
Remote code execution in APScheduler (all versions through 3.10.x and 4.0.0a5) is achievable when applications deseriali
Same weakness CWE-77 – Command Injection
View allSame technique Command Injection
View allShare
External POC / Exploit Code
Leaving vuln.today