CVE-2025-65720 GPT Researcher MCP STDIO configuration allows remote command execution
Attackers can execute arbitrary commands on victim systems via user interaction with a crafted HTML page in GPT Researcher.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2025-65720?
CVE-2025-65720 is a critical command injection vulnerability in n/a, published on 15 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-77
Which versions are affected by CVE-2025-65720?
3 open source packages ship an affected version, including gpt-researcher.
| Package | Affected | Fixed in |
|---|---|---|
gpt-researcher PyPI | From 0.14.5 to 0.14.7 | None |
gpt-researcher PyPI | From 0.14.5 to 0.14.7 | None |
gpt-researcher PyPI | From 0.14.5 to 0.14.7 | None |
How do I fix CVE-2025-65720?
No fix has been published for CVE-2025-65720 yet. Limit exposure of the affected software until one is available.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2025-65720 being exploited?
There is no known exploitation of CVE-2025-65720 in the wild and no public exploit code.
Sources
Also known as GHSA-8j86-h8gg-797p, PYSEC-2026-4219.