Skip to main content
VulnerabilityPublished Updated

CVE-2025-9556: Langchaingo supports the use of jinja2 syntax when parsing prompts, which is in turn parsed using the

Source GCVE Database

0
Compare

Not known to be exploited · CVSS 9.8 Critical.

Data as of 30 Oct 2026, 02:02 UTC

CVSS 3.1 base score
9.8Critical
How severe the flaw is on the 0–10 CVSS scale.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 12 Sep 2025

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.

What to do

AI-suggested

Until a fix is available, avoid using vulnerable versions of Langchaingo with gonja v1.5.3 or disable jinja2 syntax parsing in prompts if possible.

Description

Langchaingo versions using gonja library v1.5.3 for parsing jinja2 syntax in prompts are vulnerable to server-side template injection. This vulnerability allows attackers to inject template statements that can read sensitive files such as /etc/passwd. The flaw arises from gonja's support for include and extends syntax, which enables file reading within templates.

References

Community reviews

Loading reviews…