Langroid

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt injection (direct user input or indirect content the agent reads back via RAG), so an attacker who can influence the prompt can read or destroy all graph data and, when APOC or dbms.security procedures are enabled on the server, achieve OS-command and filesystem access. This is the same defect class and threat model as the SQLChatAgent prompt-to-SQL-to-RCE issue fixed in version 0.63.0 (CVE-2026-25879); that fix did not extend to the neo4j module. Version 0.65.5 contains a fix for the neo4j module.

Published: 2026-07-09T23:40:44.576Z
Updated: 2026-07-10T13:43:08.734Z

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with `use=False, handle=True`. Version 0.65.3 fixes the issue.

Published: 2026-07-09T23:52:11.014Z
Updated: 2026-07-10T14:23:23.640Z

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate LLM-generated tool messages with `full_eval=True`, they attempt to sandbox the execution by explicitly setting `locals` to an empty dictionary `{}` inside Python's `eval()` function. However, this relies on an incomplete understanding of Python's execution model. Because `__builtins__` is not explicitly scrubbed from the `globals` dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like `__import__('os').system()`. Since `TableChatAgent.pandas_eval()` executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.

Published: 2026-07-09T23:51:10.855Z
Updated: 2026-07-10T14:12:23.422Z

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the `SQLChatAgent` SQL-injection mitigation, with default `allow_dangerous_operations=False`, combines a raw-text regex blocklist (`_DANGEROUS_SQL_PATTERNS`) with a `sqlglot` SELECT-only statement allowlist. The blocklist entries that target callable functions require the function name to be immediately followed by `\s*\(`. PostgreSQL accepts the same call with the name separated from `(` by a quoted identifier, an inline comment, or schema qualification. These forms evade the regex, still parse as `SELECT`, and execute the same PostgreSQL function. This restores the `pg_read_file` server-side file-read primitive that the prior CVE-2026-25879 / GHSA-pmch-g965-grmr fix was meant to block: the parent advisory fixed a missing `pg_read_file` blocklist entry, while this report shows that the added regex is bypassable. Version 0.65.1 fixes the issue.

Published: 2026-07-09T23:49:52.364Z
Updated: 2026-07-10T15:27:12.550Z

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.64.0, Langroid's `ReadFileTool` and `WriteFileTool` appear to treat `curr_dir` as the intended working-directory boundary for file operations. However, the tools only change the process working directory to `curr_dir` and then operate on the user-supplied `file_path` without resolving and enforcing that the final path remains inside `curr_dir`. As a result, a tool caller can supply path traversal sequences such as `../secret.txt` to read files outside the configured current directory, or `../written_by_tool.txt` to write files outside that directory. 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. Version 0.64.0 patches the issue.

Published: 2026-07-09T23:44:46.559Z
Updated: 2026-07-14T01:25:33.853Z