CVE-2026-75858

CodeWhale rlm_eval before 0.8.64 Remote Code Execution

State
Published
Severity
8.5 High
Published
Aug 18, 2026
Updated
Aug 18, 2026
Reserved
Aug 18, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
4.08.5 HighCVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NVulnCheck
3.17.8 HighCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HVulnCheck

Weaknesses

  • CWE-94 Improper Control of Generation of Code ('Code Injection')

Affected Products

ProductVersions
CodeWhaleHmbown
  • 0.8.33 to before 0.8.41Affected
  • 0.8.41Not affected
CodeWhaleHmbown
  • 0.8.33 to before 0.8.41Affected
  • 0.8.41Not affected
CodeWhaleHmbown
  • 0.8.41 to before 0.8.64Affected
  • 0.8.64Not affected
CodeWhaleHmbown
  • 0.8.41 to before 0.8.64Affected
  • 0.8.64Not affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.