CVSS v3
8.8
HIGH
EPSS Score
1.7 %
exploit probability
CISA KEV
No
known exploited
Exploitation
—
SSVC status
Description
AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE). The vulnerability arises from the improper handling of user-supplied format strings in the `AgentOutputBlock` implementation, where malicious input is passed to the Jinja2 templating engine without adequate security measures. Attackers can exploit this flaw to execute arbitrary commands on the host system. The issue is fixed in version 0.4.0.
Technical details
- Published
- 2025-03-20
Frequently asked questions
What is CVE-2025-1040?
AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote Code Execution (RCE). The vulnerability arises from the improper handling of user-supplied format strings in the `AgentOutputBlock` implementation, where malicious input is passed to the Jinja2 templating engine without adequate security measures. Attackers can exploit this flaw to execute arbitrary commands on the host system. The issue is fixed in version 0.4.0.
Is CVE-2025-1040 actively exploited?
Active exploitation of CVE-2025-1040 has not been confirmed. The EPSS score is 1.7%, indicating the estimated probability of exploitation in the next 30 days.
What is the CVSS score for CVE-2025-1040?
CVE-2025-1040 has a CVSS v3 base score of 8.8 (HIGH severity).
Is CVE-2025-1040 affecting your environment?
Use isMalicious to check if any of your IPs or domains are associated with this vulnerability's IOCs.
No credit card required · 500 free checks/month · Free API key
Other 2025 vulnerabilities worth triaging
Ranked by exploit probability (EPSS).