- CVSS
- HIGH · 7.8v3.1CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-08-18
- Weakness
- CWE-94
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-75858
Description
CodeWhale (packages codewhale / codewhale-tui) versions >= 0.8.41 and < 0.8.64 contain a remote code execution vulnerability in the rlm_eval tool. The tool’s approval_requirement() returns ApprovalRequirement::Auto, which the engine treats as ‘never prompt,’ causing arbitrary model-supplied Python code to run in a python3 interpreter without consulting the user’s configured –approval-policy and without any approval prompt or audit step. An attacker can induce the agent to execute arbitrary code via prompt injection in untrusted content the agent reads (a web page, fetched URL, repository file, or MCP tool result); the companion rlm_open tool can stage such content. Code runs on the user’s machine at the user’s privilege level. Fixed in 0.8.64.
References
- https://github.com/Hmbown/CodeWhale/commit/57f3c89471e27ac4032d9791f6885e5d4408c381
- https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wrj3-vj8c-784f
- https://www.vulncheck.com/advisories/codewhale-rlm-eval-before-remote-code-execution
- https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wrj3-vj8c-784f
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-75858 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.