Tools AI Risk Radar ai-incident-0168
Incident record
Langflow fixes prompt-driven execution in Smart Transform
- Severity
- High
- Status
- Patched
- Type
- Prompt Injection
- Target
- langflow
- Actor
- researcher
- CVE
- CVE-2026-7700
What happened
Smart Transform ran model-generated Python with unrestricted built-ins. A malicious flow author could exploit the instructions field directly; attacker-controlled input could also trigger execution if the configured model followed injected instructions.
langflow: affected >= 1.3.0, < 1.10.3; fixed in 1.10.3. The date shown is the maintainer’s original disclosure date. Its advisory assigns 8.8 under CVSS 3.1.
Sources
- Primary disclosuregithub.com/langflow-ai/langflow/security/advisories/GHSA-9fp…
One record from the AI Risk Radar, maintained by the Security Desk.Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 13 October 2026