Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The langflow PyPI package, versions up to and including 1.8.0rc2, has a CSV Agent node that hardcodes allow_dangerous_code=True, which exposes LangChain's Python REPL tool. An attacker who can get the agent's LLM to act on injected instructions (prompt injection) can run arbitrary Python and operating system commands on the server, giving full remote code execution. The source gives no fixed version; it recommends defaulting allow_dangerous_code to False or removing it, and adding an opt-in UI toggle if the feature is needed.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 9.8 | Critical | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.35, the 98th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:07 UTC First seen by agentprime
- 31 Oct 2026, 14:07 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-3645-fxcv-hqr4
- OSV: GHSA-3645-fxcv-hqr4
- github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4
- nvd.nist.gov/vuln/detail/CVE-2026-27966
- github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508
- github.com/langflow-ai/langflow
- github.com/pypa/advisory-database/tree/main/vulns/langflow/PYSEC-2026-376.yaml
- pypi.org/project/langflow