CVE-2026-45374: CWE-94: Improper Control of Generation of Code ('Code Injection') in Hmbown CodeWhale
CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.
AI Analysis
Technical Summary
CodeWhale versions before 0.8.26 contain a code injection vulnerability (CWE-94) due to insecure default configurations in the task_create tool. Specifically, sub-agents spawned by task_create inherit allow_shell=true and auto_approve=true, allowing them to execute shell commands without explicit user approval beyond the initial task approval. This results in unapproved, unrestricted shell access to the sub-agent, effectively enabling code injection. The vulnerability is resolved in version 0.8.26.
Potential Impact
An attacker who convinces a user to approve a task_create call can cause a sub-agent to gain unrestricted shell access silently, bypassing intended approval controls. This can lead to full compromise of the affected system, including complete loss of confidentiality, integrity, and availability. The CVSS score of 9.6 reflects the critical nature of this vulnerability.
Mitigation Recommendations
Upgrade CodeWhale to version 0.8.26 or later, where this vulnerability is fixed. Since the vulnerability is resolved in this version, no additional mitigations are required beyond applying the official update. Patch status is confirmed fixed in 0.8.26.
CVE-2026-45374: CWE-94: Improper Control of Generation of Code ('Code Injection') in Hmbown CodeWhale
Description
CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.
CVSS v3.1
Score 9.6critical
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CodeWhale versions before 0.8.26 contain a code injection vulnerability (CWE-94) due to insecure default configurations in the task_create tool. Specifically, sub-agents spawned by task_create inherit allow_shell=true and auto_approve=true, allowing them to execute shell commands without explicit user approval beyond the initial task approval. This results in unapproved, unrestricted shell access to the sub-agent, effectively enabling code injection. The vulnerability is resolved in version 0.8.26.
Potential Impact
An attacker who convinces a user to approve a task_create call can cause a sub-agent to gain unrestricted shell access silently, bypassing intended approval controls. This can lead to full compromise of the affected system, including complete loss of confidentiality, integrity, and availability. The CVSS score of 9.6 reflects the critical nature of this vulnerability.
Mitigation Recommendations
Upgrade CodeWhale to version 0.8.26 or later, where this vulnerability is fixed. Since the vulnerability is resolved in this version, no additional mitigations are required beyond applying the official update. Patch status is confirmed fixed in 0.8.26.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-05-12T00:51:29.086Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a188377e29bf47b50179042
Added to database: 05/28/2026, 18:03:35 UTC
Last enriched: 06/04/2026, 20:48:32 UTC
Last updated: 07/31/2026, 19:22:59 UTC
Views: 60
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.