{"id":"CVE-2026-54051","sourceIdentifier":"security-advisories@github.com","published":"2026-07-20T17:17:57.643","lastModified":"2026-10-24T20:10:00.137","vulnStatus":"Deferred","cveTags":[],"descriptions":[{"lang":"en","value":"Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to version 5.9.1, the agent sandbox gates shell commands behind an allowlist (`SandboxPolicy.isCommandAllowed`), which THREAT_MODEL.md calls the main control against a compromised agent (Adversary 3.2). The allowlist glob-matches the whole command string, but `ShellExecutor` runs that string through `/bin/sh -c`. So any wildcard allow such as `git *`, `npm *` or `node *` also matches `git status; <anything>`, and a scoped command becomes arbitrary execution. The issue is fixed in v5.9.1. `ShellExecutor` now executes via `spawn(file, args, { shell: false })` using a quote-aware parsed argv, so no shell is invoked. `SandboxPolicy.isCommandAllowed` and the new `SandboxPolicy.tokenizeCommand` reject any unquoted shell metacharacter (`; & | $ ` ` ` ( ) < > { }` newline) or unterminated quote before the allowlist glob match; quoted metacharacters are preserved as literal argument data. Users should upgrade to `network-ai@5.9.1` or later. As defense in depth, avoid broad wildcard allowlist entries such as `node *` / `npm *` which are direct code execution by design."},{"lang":"es","value":"Network-AI es un orquestador multiagente de TypeScript/Node.js. Antes de la versión 5.9.1, el sandbox del agente restringe los comandos de shell mediante una lista de permitidos (’SandboxPolicy.isCommandAllowed’), que THREAT_MODEL.md denomina el control principal contra un agente comprometido (Adversary 3.2). La lista de permitidos realiza una coincidencia de patrones globales con toda la cadena de comandos, pero ’ShellExecutor’ ejecuta esa cadena a través de ’/bin/sh -c’. Así, cualquier permiso con comodín como ’git *’, ’npm *’ o ’node *’ también coincide con ’git status; [anything]’, y un comando con ámbito se convierte en ejecución arbitraria. El problema está solucionado en la v5.9.1. ’ShellExecutor’ ahora ejecuta a través de ’spawn(file, args, { shell: false })’ utilizando un argv analizado que tiene en cuenta las comillas, por lo que no se invoca ningún shell. ’SandboxPolicy.isCommandAllowed’ y el nuevo ’SandboxPolicy.tokenizeCommand’ rechazan cualquier metacaracter de shell sin comillas (’;’, ’&’, ’|’, ’$’, ’”’, ’(’, ’)’, ’<’, ’>’, ’{’, ’}’, salto de línea) o comilla sin cerrar antes de la coincidencia de patrones globales de la lista de permitidos; los metacaracteres entre comillas se conservan como datos de argumento literales. Los usuarios deberían actualizar a ’network-ai@5.9.1’ o posterior. Como defensa en profundidad, evite entradas amplias con comodines en la lista de permitidos como ’node *’ / ’npm *’ que son ejecución directa de código por diseño."}],"affected":[{"source":"security-advisories@github.com","affectedData":[{"vendor":"Jovancoding","product":"Network-AI","versions":[{"version":"< 5.9.1","status":"affected"}]}]}],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","baseScore":9.9,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":3.1,"impactScore":6.0}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-07-21T16:01:55.719735Z","id":"CVE-2026-54051","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"weaknesses":[{"source":"security-advisories@github.com","type":"Secondary","description":[{"lang":"en","value":"CWE-78"}]}],"references":[{"url":"https://github.com/Jovancoding/Network-AI/commit/379f77656b578144e03415c5b134d8309a4b5792","source":"security-advisories@github.com"},{"url":"https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-qw6v-5fcf-5666","source":"security-advisories@github.com"},{"url":"https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-qw6v-5fcf-5666","source":"134c704f-9b21-4f2e-91b3-4a467353bcc0"}]}