CVE-2026-75857
NVD analysis in progress
CodeWhale versions >= 0.8.41 and < 0.8.64 contain a vulnerability in the exec_shell_interact (alias exec_interact) tool, whose approval_requirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an already-approved long-running interactive shell (e.g., a python3 -i REPL, mysql, ssh, or sudo -i session) without any approval prompt. An attacker who can inject instructions via untrusted content the agent ingests (a fetched page, MCP result, or repo file) can cause commands to run at the privilege level of that approved process. Fixed in 0.8.64.
What this means
- Exposure
- Exploitable with local access to the machine and without authentication — but only if a user opens booby-trapped content. The attack does require particular conditions, which makes it less systematic.
- Impact
- An attacker can read sensitive data, modify or destroy data and take the service offline.
- Weakness
- Privilege handling is faulty, so an account ends up with more rights than intended.
- Likelihood
- Its EPSS score stays low: nothing points to imminent exploitation, which is no reason to leave it unpatched.
What to doFold into the next patch cycle.
Read automatically from the CVSS vector, the weakness type (CWE) and the EPSS score. The technical description above remains the one published by NIST.