Skip to content
Fencer Vulns
critical 9.8

CVE-2026-37003 json

Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via prompt injection.

published 2026-08-27 2 mo ago modified 2026-09-08 2 mo ago also EUVD-2026-67272

cvss
9.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.3%
EPSS 1.3% chance of exploitation in 30 days, percentile 71%
public exploits
0
none known

Summary

Agno up to and including 2.5.8 is vulnerable to Remote Code Execution (RCE) via prompt injection. The PythonTools and ShellTools components pass unsanitized, LLM-generated arguments directly to execution sinks including exec(), runpy.run_path(), and subprocess.run(). An unauthenticated attacker can exploit this by embedding malicious instructions in content processed by the agent (such as web pages or documents), allowing for arbitrary code and OS command execution on the host server.

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
total
Assessed
2 mo ago

Exploit prediction

1.32% chance of exploitation in the next 30 days, higher than 71% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CISA ADP 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Classification

Weakness
  • CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.