vulnerability / NVI-00014045 / Revision 1
CodeWhale: rlm_eval auto-approves arbitrary Python execution, bypassing the user's approval policy (RCE)
GitHub lists this reviewed advisory for deepseek-tui, deepseek-tui, codewhale-tui, codewhale. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.
This report has not inspected your inventory, configuration, deployed build, reachability or evidence. A catalog listing and a severity score do not establish exposure or compromise.
01 / Meaning
Why it matters
Published affected context helps an owner decide what evidence to gather. This report has not examined your application.
7.8 high
GitHub source severity; exploitability and local consequence require separate evidence.
As of · GitHub Advisory Database
02 / Applicability
The affected context
Affected versions, configuration prerequisites and known exclusions are public. Confirm each one against the deployed service.
deepseek-tui
source listed>= 0.8.33, <= 0.8.41
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is preserved below. ### Summary The `rlm_eval` tool runs an arbitrary Python string chosen by the model in a real `python3` interpreter. Its `approval_requirement()` returns `ApprovalRequirement::Auto`, which the engine treats as "never prompt," regardless of the user's configured `--approval-policy`. A single tool call — which prompt injection from any untrusted content the agent reads (a web page, a fetched URL, a repo file, an MCP tool result) can induce — runs code on the user's machine at the user's privilege with no prompt and no audit step. This is the same defect that was already patched on the sibling `run_tests` tool (CVE-2026-45311); the fix never reached `rlm_eval` or `rlm_open`, which expose a broader surface (full Python on the host, not just `cargo test`). ### Details `rlm_eval`'s `execute()` reads the LLM-controlled `code` field and runs it (`crates/tui/src/tools/rlm.rs:
deepseek-tui
source listed>= 0.8.33, < 0.8.41
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is preserved below. ### Summary The `rlm_eval` tool runs an arbitrary Python string chosen by the model in a real `python3` interpreter. Its `approval_requirement()` returns `ApprovalRequirement::Auto`, which the engine treats as "never prompt," regardless of the user's configured `--approval-policy`. A single tool call — which prompt injection from any untrusted content the agent reads (a web page, a fetched URL, a repo file, an MCP tool result) can induce — runs code on the user's machine at the user's privilege with no prompt and no audit step. This is the same defect that was already patched on the sibling `run_tests` tool (CVE-2026-45311); the fix never reached `rlm_eval` or `rlm_open`, which expose a broader surface (full Python on the host, not just `cargo test`). ### Details `rlm_eval`'s `execute()` reads the LLM-controlled `code` field and runs it (`crates/tui/src/tools/rlm.rs:
codewhale-tui
source listed>= 0.8.41, < 0.8.64
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is preserved below. ### Summary The `rlm_eval` tool runs an arbitrary Python string chosen by the model in a real `python3` interpreter. Its `approval_requirement()` returns `ApprovalRequirement::Auto`, which the engine treats as "never prompt," regardless of the user's configured `--approval-policy`. A single tool call — which prompt injection from any untrusted content the agent reads (a web page, a fetched URL, a repo file, an MCP tool result) can induce — runs code on the user's machine at the user's privilege with no prompt and no audit step. This is the same defect that was already patched on the sibling `run_tests` tool (CVE-2026-45311); the fix never reached `rlm_eval` or `rlm_open`, which expose a broader surface (full Python on the host, not just `cargo test`). ### Details `rlm_eval`'s `execute()` reads the LLM-controlled `code` field and runs it (`crates/tui/src/tools/rlm.rs:
codewhale
source listed>= 0.8.41, < 0.8.64
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is preserved below. ### Summary The `rlm_eval` tool runs an arbitrary Python string chosen by the model in a real `python3` interpreter. Its `approval_requirement()` returns `ApprovalRequirement::Auto`, which the engine treats as "never prompt," regardless of the user's configured `--approval-policy`. A single tool call — which prompt injection from any untrusted content the agent reads (a web page, a fetched URL, a repo file, an MCP tool result) can induce — runs code on the user's machine at the user's privilege with no prompt and no audit step. This is the same defect that was already patched on the sibling `run_tests` tool (CVE-2026-45311); the fix never reached `rlm_eval` or `rlm_open`, which expose a broader surface (full Python on the host, not just `cargo test`). ### Details `rlm_eval`'s `execute()` reads the LLM-controlled `code` field and runs it (`crates/tui/src/tools/rlm.rs:
03 / Response
What to do next
- investigate
Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.
Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system. GitHub Advisory Database
A fixed release is not deployment evidence.
Check current vendor support and compatibility. After making a change, verify the deployed build and relevant runtime conditions. Keep the evidence, owner and time. An updated lockfile alone does not prove what is running.
04 / Limits
What this report cannot establish
- Customer inventory, deployment, reachability and exploitation have not been inspected.
05 / Provenance
Sources you can inspect
Each assertion retains its source. Mirrored records may repeat one underlying publisher; additional links are not independent corroboration.
- GHSA-wrj3-vj8c-784f ↗
GitHub Advisory Database · vendor advisory
Observed . GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.
Public revision history
Only published revisions appear here. Routine fetches do not create a material-change event.
- Revision 1 ·
First indexed by Null; source disclosure date is shown separately.