llamaCVEVulnerability Intelligence
/
Advisory · GitHub · crates.io · codewhale-tui

GHSA-3MGH-93R5-R7JF

CodeWhale: exec_shell parallel-readonly classifier auto-approves fd/rg/git grep exec flags enabling silent RCE

Parche disponible
Descargar PNG JSON
CVSS 3.1
8.1
Alta
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H Fuente: GitHub
ExplotaciónSin evidenciaNo figura en CISA KEV
Exploits públicos0Ninguno conocido
Parche1 versiónPrimer parche a -126 d de la divulgación
Exposición7 hDesde la divulgación, 19 nov 2026, 5:48 p. m.
Detección1 minDesde la divulgación hasta su ingreso al índice
Timeline

Ciclo de vida de la vulnerabilidad

Hoy
Divulgación
Publicada +1
Explotación
Remediación
Parche 0.9.0
Monitoreo
Detectada
Fuente: GitHub Security Advisories +2
16 jul 26
18 nov 26
19 nov 26
20 nov 26
16 jul 26
17 ago 26
18 sept 26
19 oct 26
20 nov 26
FechaFaseEventoDetalle
Remediación Parche 0.9.0 codewhale-tui · -126 d desde divulgación
Monitoreo Detectada Ingresó al índice
Divulgación Publicada GHSA-3MGH-93R5-R7JF divulgada · CVSS 8.1 (GitHub)
Divulgación Modificada Última actualización del registro
Monitoreo Fuente: GitHub Security Advisories Registro visto por primera vez en GitHub Security Advisories
Monitoreo Fuente: OSV Registro visto por primera vez en OSV
Monitoreo Verificada Última verificación contra las fuentes
Resumen
Descripción del advisory
Texto original · GitHub · en inglés
Maintainer resolution

The CodeWhale maintainers validated this report. CodeWhale 0.8.67 and earlier are affected. Version 0.9.0 contains the fix in commit 208421b9d23d81cea3311a1eeb2a2ea81d637686. Users should upgrade to 0.9.0 or later. The original reporter analysis is preserved below.

## Summary
The interactive Agent profile of DeepSeek-TUI (CodeWhale) is explicitly documented to gate every shell command behind an approval prompt (config.rs:3725-3736). However, `ExecShellTool::approval_requirement_for(&tool_input)` downgrades the requirement from `Required` to `Auto` for any command the classifier deems "parallel read-only" (shell.rs:2314-2320). `registered_tool_approval_required` returns `false` for `Auto` before the `auto_approve` check runs (turn_loop.rs:37-38), so no prompt is shown even for a user who never enabled YOLO. The classifier `is_parallel_readonly_command` (command_safety.rs:389) rejects only shell metacharacters and then matches the flag-stripped base command name against an allowlist that includes `fd`, `rg`, and `git grep`. Those tools execute arbitrary external programs through documented flags (`fd -x/--exec`, `rg --pre`, `git grep --open-files-in-pager`) that need no shell metacharacters — yielding silent arbitrary-program execution in the default profile. Same silent-RCE class as CVE-2026-45311 (run_tests) but via a different, unpatched tool and code path.

## Root Cause
`approval_requirement_for` downgrades `exec_shell` to `Auto` when `exec_shell_input_is_parallel_readonly` returns true (shell.rs:2314-2320). The classifier strips all flags and matches the base command name against `PARALLEL_READONLY_PREFIXES` (command_safety.rs:363-385, 419-433). `fd`/`rg` are absent from `COMMAND_ARITY`, so `fd -x cp {} /tmp/exfil` canonicalizes to `"fd"` ∈ allowlist. The only remaining gate at the execute sink is `analyze_command`, which rates `fd`/`rg` as `Safe` (SAFE_COMMANDS command_safety.rs:527,530), so the `SafetyLevel::Dangerous`-only block (shell.rs:2408) never fires. Default execpolicy is empty (engine.rs:494) → Skip. Interactive-origin auto_review safety_floor holds only `Publish` (auto_review.rs:344-357), not interactive shell.

## Impact
Arbitrary external program execution (any binary, any argv, including a repo-committed script) on the developer host, with no approval prompt, in the default interactive Agent profile — bypassing the boundary config.rs:3725-3736 explicitly promises. Identical outcome to seed CVE-2026-45311 via a different, unpatched tool.

## Proof of Concept
Model coerced (via indirect prompt injection from repo file / issue / fetched page — the seed threat model, in scope per SECURITY.md:48) to emit:

{"name":"exec_shell","arguments":{"command":"fd -u -tf -x ./pwn.sh"}}

Alternatives (all metachar-free, all auto-approved): `fd -tf -x cp {} /tmp/exfil`; `rg --pre /tmp/evil.sh --pre-glob '*' needle .`; `git grep --open-files-in-pager=/tmp/evil.sh needle`.

## Attack Chain
1. Entry. Agent ingests attacker-controlled content; injected instruction coerces the model to emit `exec_shell {"command":"fd -u -tf -x ./pwn.sh"}`.
- Guard: none — reading content and model tool-calls are by design (seed threat model: indirect prompt injection).
- Bypass proof: n/a (in-scope by design per SECURITY.md:48).
2. Gate — approval requirement. turn_loop.rs:1738 → `spec.approval_requirement_for(&input)` → shell.rs:2314-2320 `exec_shell_input_is_parallel_readonly`.
- Guard: metachar filter (command_safety.rs:394-400) + base-name allowlist.
- Bypass proof: the string contains none of `; & | > < \` $(` or newlines; `-x <program> <args>` is `fd`'s own exec mechanism (no shell). `classify_command` strips `-u -tf -x`, positionals `[fd, ./pwn.sh]`; `fd` ∉ `COMMAND_ARITY` → canonical `"fd"` ∈ `PARALLEL_READONLY_PREFIXES` → returns true. Maintainer test `parallel_readonly_command_classifier_is_strict` (command_safety.rs:1162+) confirms bare `fd`/`rg` classify parallel-readonly.
3. Gate — prompt decision. `registered_tool_approval_required(name, Auto, auto_approve)`.
- Guard: the approval prompt itself.
- Bypass proof: `requirement == Auto` returns `false` at turn_loop.rs:37-38 unconditionally, before `!auto_approve`. No prompt regardless of user settings. Empty execpolicy → Skip; interactive safety_floor returns NoChange for fd.
4. Sink. `ExecShellTool::execute` (shell.rs:2334) → `analyze_command`.
- Guard: `SafetyLevel::Dangerous` block (shell.rs:2408).
- Bypass proof: `fd` ∈ `SAFE_COMMANDS` (command_safety.rs:530) → `analyze_command` returns `Safe`; not `Dangerous` → not blocked. Child runs the attacker's program.
5. Impact. Silent arbitrary-program execution on the developer host, no approval prompt, default interactive Agent profile.

## Bypass Evidence
- Present on latest release tag v0.8.67: turn_loop.rs:37-38 `Auto`→`return false`; shell.rs:2314-2320 override; command_safety.rs allowlist includes `"rg"`,`"fd"`,`"git grep"`; SAFE_COMMANDS includes `"rg"`,`"fd"`; `fd`/`rg` absent from `COMMAND_ARITY`. command_safety.rs / turn_loop.rs finding-critical functions byte-identical v0.8.67↔HEAD.
- Maintainer's own test `parallel_readonly_command_classifier_is_strict` confirms bare `rg`/`fd` classify parallel-readonly and only metachar forms are rejected.

## Affected Versions
`<= 0.8.67` (present on latest release tag v0.8.67 and HEAD 6a3403e).

## Suggested Fix
Remove exec-capable tools (`fd`, `rg`, `git grep`) from `PARALLEL_READONLY_PREFIXES`, or make the classifier reject their exec flags (`-x`/`--exec`, `--pre`, `--open-files-in-pager`), so a code-executing invocation cannot be auto-approved as read-only.

Reported by zx (Jace)

Incluye detalles técnicos publicados por el investigador. Úselos solo para validar y corregir sus propios sistemas.

Vector CVSS 3.1

Desglose de métricas

Opción resaltada = valor del vector · izquierda = peor caso · GitHub
Vector de ataqueAV:N
RedAdyacenteLocalFísica
ComplejidadAC:H
BajaAlta
PrivilegiosPR:N
NingunoBajosAltos
InteracciónUI:N
NingunaRequerida
AlcanceS:U
CambiadoSin cambio
ConfidencialidadC:H
AltoBajoNinguno
IntegridadI:H
AltoBajoNinguno
DisponibilidadA:H
AltoBajoNinguno
Versiones

Rangos afectados

Afectada Corregida Última
codewhale-tui · codewhale< 0.9.0
0.9.0
0.10.2
Remediación

Estado del parche por paquete

Paquete / productoEstadoCorregida enDesde divulgaciónÚltima versión
crates.iocodewhale-tui
Corregida 0.9.0 -126 d 0.10.2 no afectada
npmcodewhale
Corregida 0.9.0 -126 d 0.10.2 no afectada
Versiones corregidas0.9.0
Explotación

Arsenal público

Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.

Referencias
Advisoryhttps://nvd.nist.gov/vuln/detail/CVE-2026-83816
Otrahttps://github.com/codewhale-hq/Codewhale/security/advisories/GHSA-3mgh-93r5-r7jf
Otrahttps://github.com/codewhale-hq/Codewhale/commit/208421b9d23d81cea3311a1eeb2a2ea81d637686
Otrahttps://github.com/codewhale-hq/Codewhale
Otrahttps://github.com/codewhale-hq/Codewhale/releases/tag/v0.9.0

Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.