Codewhale

CodeWhale versions >= 0.3.27 and < 0.8.64 (published as deepseek-tui >= 0.3.27 and < 0.8.41 on npm and 0.3.27 through 0.8.41 on crates.io, and as codewhale / codewhale-tui >= 0.8.41 and < 0.8.64) contain an argument injection vulnerability in the git_show tool. The model-supplied rev parameter is passed unvalidated into the git show argv without an --end-of-options sentinel, so a value beginning with --output= is interpreted as a git flag. Because the tool is registered as auto-approved and advertised as read-only, an attacker (via a malicious repository combined with prompt injection) can cause an unprompted arbitrary file write at the privilege of the invoking user, targeting sensitive files such as ~/.ssh/authorized_keys, ~/.bashrc, or ~/.gitconfig. Fixed in codewhale / codewhale-tui 0.8.64 by adding rev validation; the deprecated deepseek-tui crate has no fixed release.

Published: 2026-08-18T15:22:01.505Z
Updated: 2026-10-29T21:16:54.792Z

CodeWhale versions >= 0.3.10 and < 0.8.64 (published as deepseek-tui >= 0.3.10 and < 0.8.41 on npm and 0.3.10 through 0.8.41 on crates.io, and as codewhale / codewhale-tui >= 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 codewhale / codewhale-tui 0.8.64; the deprecated deepseek-tui crate has no fixed release.

Published: 2026-08-18T15:21:56.357Z
Updated: 2026-10-29T21:16:54.116Z

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.

Published: 2026-05-28T17:26:42.979Z
Updated: 2026-05-30T02:04:52.694Z

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, although SSRF is validated against hostnames that resolve to private IPv6 addresses, when providing the IPV6 in‌‌ URL‌ as http://[::1], the SSRF defenses do not work. This vulnerability is fixed in 0.8.26.

Published: 2026-05-28T17:27:59.055Z
Updated: 2026-05-30T02:05:45.704Z

CodeWhale is a DeepSeek + MiMo coding agent in terminal. From 0.3.0 to 0.8.23, the run_tests tool executes cargo test in the workspace with ApprovalRequirement::Auto, meaning it runs without any user approval prompt. cargo test compiles and executes arbitrary code: test binaries, build.rs build scripts, and proc macros. While auto-approving test execution is a deliberate design choice, it creates an inconsistency in the security boundary. However, in a malicious repository, test code can execute arbitrary shell commands, exfiltrate credentials, or establish persistence with zero approval. The attack is amplified by AGENTS.md (auto-loaded into the system prompt), which can instruct the model to run tests proactively at session start. This vulnerability is fixed in 0.8.23.

Published: 2026-05-28T17:32:26.950Z
Updated: 2026-06-01T19:09:50.099Z