Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring th
CVE-2026-55615 · GHSA-2pq5-3q89-j7cc · published 2026-07-06
- Severity
- Critical
- CVSS score
- 9.2
- Chance of exploitation (EPSS)
- 0.46%
- Fixed in
- 0.65.5
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Total
- CISA SSVC
An attacker who can influence the agent prompt (directly, or indirectly via content the agent reads back through RAG) controls the executed Cypher. Floor (no extra config, not contingent): unauthorized read of all graph data via cypher_retrieval_tool and full write/destroy (including MATCH (n) DETACH DELETE n) via cypher_creation_tool, plus the built-in LOAD CSV remote-fetch (SSRF) primitive. Ceiling (config-conditional, when APOC / dbms.security procedures are granted to the DB role, a common deployment): apoc.load. (SSRF + remote/local file read), apoc.cypher.runFile / apoc.import. / apoc.export. (filesystem), and CALL dbms. …
Upgrade langroid to 0.65.5 or later.
Mirror the SQLChatAgent fix in the neo4j module: (1) add allow_dangerous_operations: bool = False to Neo4jChatAgentConfig with a read-only default for cypher_retrieval_tool; (2) add a _validate_cypher(query, write) method that, unless allow_dangerous_operations is True, blocks CALL apoc., CALL dbms., CALL db. admin procedures, LOAD CSV, and any procedure/function touching filesystem/network/OS, and (for the read path) rejects write clauses (CREATE/MERGE/SET/DELETE/DETACH DELETE/REMOVE/DROP); (3) enforce it before session.run (read_query :223) and tx.run (write_query :276), returning the rejection to the LLM the way run_query does at sql_chat_agent.py:721; (4) document, as the SQL config doe…
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| langroid | PyPI | <= 0.65.4 | 0.65.5 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- 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
- HighLangroid: handle_message() executes user-supplied tool JSON without sender verificationlangroid
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.