CVE-2026-109444

8.8High

Published 20 Oct 2026 · NVD status: Received · AI triage by gemini-3.8-flash

8.8High

Attack vector: Network
Complexity: Low
Privileges needed: None
User interaction: Required
Impact: Full C/I/A compromise
Weakness: CWE-862

Impact

Remote attackers can execute arbitrary shell commands on the host to exfiltrate LLM, Slack, and cloud credentials. They achieve this via prompt injection in alerts or Slack messages that the agent triages.

Root cause

The headless presenter's execution_allowed() function always returns True, completely bypassing the shell_run command confirmation approval gate.

Affected systems

OpenSRE through 0.1.2026.10.19

CVSS v3.1 · CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Fix & remediation

Upgrade to a version past 0.1.2026.10.19 once released. If an update is unavailable, disable or remove the shell_run tool and shut down the Slack transport dispatcher immediately.

shell

$ pip install --upgrade opensre

AI-suggested. Run it in staging first and check it against the vendor advisory. Why?

Ad · In-content banner

NVD description

OpenSRE through 0.1.2026.10.19 contains an approval gate bypass vulnerability that allows attackers to execute shell_run commands without confirmation because the headless presenter's execution_allowed() always returns True. Attackers can inject instructions into alerts or Slack messages triaged by the agent to run commands on the host and exfiltrate LLM, Slack and cloud credentials.

References

Source: nvd.nist.gov/vuln/detail/CVE-2026-109444