CVE-2026-75858
CodeWhale (packages codewhale / codewhale-tui) versions >= 0.8.41 …
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.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/Hmbown/CodeWhale/commit/57f3c89471e27ac4032d9791f6885e5d4408c381
- github.com/Hmbown/CodeWhale/security/advisories/GHSA-wrj3-vj8c-784f
- www.vulncheck.com/advisories/codewhale-rlm-eval-before-remote-code-execution
- nvd.nist.gov/vuln/detail/CVE-2026-75858
- github.com/advisories/GHSA-wrj3-vj8c-784f
- nvd.nist.gov/vuln/detail/CVE-2026-75858
- cve.org/CVERecord?id=CVE-2026-75858
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.