Am I affected by CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an…? What should I do?

Question

`exec_shell_interact` returns `ApprovalRequirement::Auto`, so when the model writes input into a shell the user already approved, no prompt fires. Affected: codewhale-tui >= 0.8.41, < 0.8.64; codewhale >= 0.8.41, < 0.8.64. Fixed in: 0.8.64. What should you check, and what should you do about it? Full incident page with sources: https://agentarmorhq.com/incidents/2026/09/cve-2026-75857-codewhale

AgentArmorHQ team · Accepted Answer

**Am I affected?** Affected: codewhale-tui >= 0.8.41, < 0.8.64; codewhale >= 0.8.41, < 0.8.64. Fixed in: 0.8.64. - Check your version: run `cargo tree -i deepseek-tui`. Versions >= 0.3.10, <= 0.8.41 of deepseek-tui are affected. - Check your version: run `npm ls deepseek-tui`. Versions >= 0.3.10, < 0.8.41 of deepseek-tui are affected. - Check your version: run `cargo tree -i codewhale-tui`. Versions >= 0.8.41, < 0.8.64 of codewhale-tui are affected. **What to do now** 1. Upgrade to the fixed version: run `npm install deepseek-tui@0.8.41` (first patched version 0.8.41). 2. Upgrade to the fixed version: run `cargo update -p codewhale-tui --precise 0.8.64` (first patched version 0.8.64). 3. Upgrade to 0.8.64 or later. General practice, not from the source: if the affected software could read tokens or credentials, rotate them after upgrading; pin versions and review changes before updating tools your agents run. **Sources** - GitHub Advisory Database: https://github.com/advisories/GHSA-g29h-pfmp-qp9r Full incident page: https://agentarmorhq.com/incidents/2026/09/cve-2026-75857-codewhale

Am I affected by CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an…? What should I do?

1 answer

Add your answer or comment