CVE-2026-9196
published 2026-08-05CVE-2026-9196: IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper…
PriorityP358high8.8CVSS 3.1
AVNACLPRLUINSUCHIHAH
EPSS
0.27%
18.6th percentile
IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user approval, which may allow an attacker to trigger side effects such as outbound network access, file system interaction, or data exfiltration with the privileges of the Langflow backend process.
Affected
2 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| ibm | langflow_oss | 1.0.0 – 1.10.3 | — |
| langflow | langflow | >= 1.0.0 < 1.11.0 | 1.11.0 |
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
VulDB
IBM Langflow OSS up to 1.10.3 Agentic Assistant Validation code injection
vuldb·2026-08-05·CVSS 8.1
CVE-2026-9196 [HIGH] IBM Langflow OSS up to 1.10.3 Agentic Assistant Validation code injection
A vulnerability described as critical has been identified in IBM Langflow OSS up to 1.10.3. The affected element is an unknown function of the component Agentic Assistant Validation. The manipulation results in code injection.
This vulnerability is known as CVE-2026-9196. It is possible to launch the attack remotely. No exploit is available.
GHSA
IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components.
ghsa_unreviewed·2026-08-05
CVE-2026-9196 [HIGH] CWE-94 IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components.
IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user approval, which may allow an attacker to trigger side effects such as outbound network access, file system interaction, or data exfiltration with the privileges of the Langflow backend process.
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2026-08-05
Published