Langroid

A high-severity vulnerability, CVE-2026-54771, in Langroid applications allows untrusted users to directly invoke internal tools via raw JSON payloads, even when these tools are configured not to be used by the LLM, enabling malicious actors to bypass security controls and execute sensitive operations like file read/write, database queries, or access to internal orchestration tools.

Langroid is vulnerable to a critical Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` components when `full_eval=True` due to CVE-2026-54769; the `eval()` function fails to properly scrub `__builtins__` from `globals`, allowing attackers to inject `__import__('os').system()` calls via crafted prompt payloads, leading to unauthenticated RCE, unauthorized data access, or system compromise on the host running the Langroid agent.

A path traversal vulnerability (CVE-2026-50181) exists in Langroid's `ReadFileTool` and `WriteFileTool` components (versions <= 0.63.0), allowing an attacker to read or write arbitrary files outside the configured `curr_dir` via crafted `file_path` arguments, potentially leading to sensitive information disclosure or unauthorized file modification in applications exposing these tools to user or LLM input.