Unauthenticated code execution via CSV Agent prompt injection
Published Aug 4, 2026 · Updated Aug 4, 2026
Code injection in Flowise before 3.1.3 allows remote attackers to execute arbitrary code through prompts sent to a CSV Agent chatflow. CSV_Agents.run places user input in an LLM prompt, passes the returned Python through a bypassable regex blocklist, and evaluates it in unsandboxed Pyodide. Exploitation requires a reachable chatflow configured with the CSV Agent and an LLM; successful code runs with the service account's privileges.
Summary
What happened
Code injection in Flowise before 3.1.3 allows remote attackers to execute arbitrary code through prompts sent to a CSV Agent chatflow. CSV_Agents.run places user input in an LLM prompt, passes the returned Python through a bypassable regex blocklist, and evaluates it in unsandboxed Pyodide. Exploitation requires a reachable chatflow configured with the CSV Agent and an LLM; successful code runs with the service account's privileges.
The record
- CVE
- CVE-2026-70477
- Published
- Aug 4, 2026
- Updated
- Aug 4, 2026
- Vendor
- FlowiseAI
- Product
- Flowise
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 4, 2026CVE publishedPublication date reported by the CVE source.
- Aug 4, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 3.1.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-5xvg-pmgg-3mxr poc.pyproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo