Skip to content
Fencer Intel
critical 9.8

CVE-2026-109437 json

Cognition < 0.13.0 Unauthenticated RCE via Local Shell Backend

published 21d ago modified 17d ago also EUVD-2026-104570

cvss
9.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.8%
EPSS 0.8% chance of exploitation in 30 days, percentile 56%
public exploits
0
none known

Summary

Cognition before 0.13.0 contains an unauthenticated remote code execution vulnerability due to defaulting its agent sandbox backend to local execution and shipping no authentication on its REST/SSE API. Attackers can create a session via POST /sessions and post a message via POST /sessions/{id}/messages without credentials, causing the Deep Agents ReAct loop to run attacker-directed shell commands through the local shell backend, resulting in remote code execution as the server process.

Patch / fix

  • CognicellAI Cognition 0.13.0

Is CVE-2026-109437 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
20d ago

Exploit prediction

0.78% chance of exploitation in the next 30 days, higher than 56% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • lasso.security https://www.lasso.security/vulnerability-database/cve-2026-109437 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 4.0 9.2 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CNA 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA 4.0 9.2 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Affected products

  • CognicellAI Cognition

Classification

Weakness
  • CWE-1188 Initialization of a Resource with an Insecure Default
  • CWE-306 Missing Authentication for Critical Functionality

References

Sources

Fencer Intel 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.