Langroid: Path traversal in the file tools allows read/write outside configured current directory
CVE-2026-50181 · GHSA-fg23-3346-88f5 · published 2026-07-02
- Severity
- High
- CVSS score
- 7.1
- Chance of exploitation (EPSS)
- 0.18%
- Fixed in
- 0.64.0
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
Langroid's ReadFileTool and WriteFileTool appear to treat currdir as the intended working-directory boundary for file operations. However, the tools only change the process working directory to currdir and then operate on the user-supplied filepath without resolving and enforcing that the final path remains inside currdir. This can impact applications that expose Langroid file tools to an LLM agent, user-controlled tool call, or delegated coding/documentation agent while relying on curr_dir to restrict file access to a project/workspace directory.
Upgrade langroid to 0.64.0 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| langroid | PyPI | <= 0.63.0 | 0.64.0 |
- CriticalMCP Path Traversal Allows Full-Filesystem Read and JWT Secret Exfiltration Leading to Account Takeoverlangflow, langflow-base
- Critical@zereight/mcp-gitlab: Unauthenticated arbitrary file read via `upload_markdown` enables PAT exfiltration and full account takeover@zereight/mcp-gitlab
- CriticalFlowise RCE via SQL Database Chain Nodeflowise, flowise-components
- Criticalfast-mcp-telegram: Bearer token path traversal bypasses reserved Telegram session protectionfast-mcp-telegram
- CriticalMCP Toolbox HTTP tool path parameters allow traversal to unintended endpointsgithub.com/googleapis/mcp-toolbox
- CriticalLangflow: BaseFileComponent-based nodes arbitrary file read with RCE exploitlangflow
- CriticalLangroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring thlangroid
- CriticalLangroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file callslangroid
- CriticalLangroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgentlangroid
- CriticalLangroid has Prompt to SQL Injection, Leading to RCElangroid
- CriticalLangroid has WAF Bypass Leading to RCE in TableChatAgentlangroid
- CriticalLangroid has a Code Injection vulnerability in TableChatAgentlangroid
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.