GHSA-f228-chmx-v6j6: Flowise: Remote code execution vulnerability in AirtableAgent.ts caused by lack of input verification when using `Pandas`.

Summary

The AirtableAgent node in FlowiseAI passes user input directly into the question parameter of an LLM prompt template, and the generated output is executed as Python code through Pyodide and Pandas without sanitization. An attacker can bypass the intended LLM behavior with a prompt injection and achieve remote code execution. The advisory is tracked as GHSA-f228-chmx-v6j6.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

• flowisenpmLLM dependency since 2024-03-12
• flowise-componentsnpmLLM dependency since 2023-04-10 · 1 tracked dependent

Related items

• HighCVE-2026-76066: IntentKit authorization bypass lets callers execute owner-restricted toolsSimilar attack · NVD/CVE Database
• LowJev as a judge: How counterfeit policy steers JevSimilar attack · Datadog Security Labs
• LowAgents at the Edge: Extending AI Security Governance to Physical AI with DefenseClawSimilar attack · Cisco AI Blog
• InfoMMA-SafetyBench: A Benchmark for Multimodal Agent Safety EvaluationSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoPolicy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy RewardsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)