CVE-2026-75857
HIGH
7,3
Source: [email protected]
Attack Vector: local
Attack Complexity: high
Privileges Required: none
User Interaction: passive
Confidentiality: N/A
Integrity: N/A
Availability: N/A
HIGH
7,0
Source: [email protected]
Attack Vector: local
Attack Complexity: high
Privileges Required: none
User Interaction: required
Scope: unchanged
Confidentiality: high
Integrity: high
Availability: high
Description
AI Translation Available
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.
269
Improper Privilege Management
DraftCommon Consequences
Security Scopes Affected:
Access Control
Potential Impacts:
Gain Privileges Or Assume Identity
Applicable Platforms
All platforms may be affected
https://github.com/Hmbown/CodeWhale/commit/57f3c89471e27ac4032d9791f6885e5d4408…
https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-g29h-pfmp-qp9r
https://www.vulncheck.com/advisories/codewhale-before-privilege-escalation-via-…