Habilidades voice-agent-expert

📦

voice-agent-expert

Name: voice-agent-expert
Author: EGAdams

Revisión del contenido r1 Riesgo alto 📁 Acceso al sistema de archivos🌐 Acceso a red⚙️ Comandos externos🔑 Variables de entorno

Solucionar problemas de agentes de voz LiveKit Letta

Los fallos de los agentes de voz son difíciles de diagnosticar cuando interactúan el audio, WebRTC, los tokens y el estado del proceso. Esta skill proporciona comprobaciones, flujos de trabajo y scripts auxiliares enfocados para la depuración de LiveKit y Letta.

Compatible con: Claude Codex Code(CC)

⚠️ 38 Deficiente

Maintain this Skill? Claim it ⚠️ 38 Deficiente

Detente y solicita confirmación antes de instalar.

Revisa el plan y obtén el consentimiento explícito del usuario antes de modificar archivos.

Instalar con mi Agente

Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.

Solicitud de agente

Review the Skillstore skill "voice-agent-expert" from https://skillstore.io/skills/egadams-voice-agent-expert.md and its manifest at https://skillstore.io/api/skills/egadams-voice-agent-expert/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.

Recursos legibles por agentes

Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.

Detalle Markdown GET /skills/egadams-voice-agent-expert.md Manifest firmado GET /api/skills/egadams-voice-agent-expert/manifest Lockfile firmado GET /api/skills/egadams-voice-agent-expert/lockfile

Pruébalo

Usando "voice-agent-expert". Mi agente de voz se une a la sala pero nunca responde.

Resultado esperado:

Causa probable: workers de voice-agent duplicados o el hook de LiveKit incorrecto.
Confirma que solo haya un worker activo y que las pruebas locales usen el modo DEV.
Revisa los registros en busca del marcador de enrutamiento que demuestra que Letta está recibiendo mensajes.

Usando "voice-agent-expert". El playground dice que mi token no es válido.

Resultado esperado:

Genera un nuevo token de LiveKit porque los tokens caducan después de varias horas.
Confirma que la URL de LiveKit coincida con el endpoint del servidor usado por el navegador.
Trata el token como información sensible y evita compartir registros que lo contengan.

Usando "voice-agent-expert". El audio se corta después de unos segundos.

Resultado esperado:

Comprueba si hay workers de voice-agent duplicados antes de cambiar la configuración del modelo o del audio.
Reinicia el worker limpiamente después de detener procesos obsoletos y limpiar salas obsoletas.
Verifica que el worker activo sea el que está recibiendo los registros actuales.

Auditoría de seguridad

Riesgo alto

v8 • 6/7/2026 Abrir el informe versionado

The skill appears intended for local LiveKit and Letta debugging, not covert exfiltration. Several findings are confirmed because helper scripts read .env files, handle API secrets, spawn shell commands, and start local services with hardcoded paths. Many markdown backtick and localhost URL findings are false positives, but the package needs hardening before broad marketplace distribution.

Archivos escaneados

685

Líneas analizadas

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (8)

Alto

scripts/diagnose_voice_system.py:68

Environment file access

livekit_env = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/diagnose_voice_system.py:69

Environment file access

planner_env = Path("/home/adamsl/planner/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/diagnose_voice_system.py:111

Environment file access

print("export $(grep -v '^#' /home/adamsl/ottomator-agents/livekit-agent/.env | xargs)")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:9

Environment file access

env_file = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/start_voice_system.py:61

Environment file access

env_file = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/start_voice_system.py:71

Environment file access

planner_env = Path("/home/adamsl/planner/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

SKILL.md:35-44 QUICK_REFERENCE.md:124-130

Broad Process Termination Instructions

The reset guidance tells users to kill LiveKit and voice-agent processes before restarting services. Broad process matching can disrupt unrelated local work if run without confirmation.

Both cited sections contain process-kill and restart guidance for local services. The commands are operationally plausible and not merely scanner artifacts.

Medio

scripts/generate_token.py:44-53

Connection Token Printed to Terminal

The token generator creates a LiveKit JWT and prints it directly to terminal output. This is useful for setup but can leak session access through copied logs.

The code directly creates a JWT and prints it under a token label. The behavior is intentional, but the token is still sensitive.

Elementos de revisión de capacidades (32)

Estas son capacidades locales reales que pueden esperarse para esta habilidad, por lo que requieren revisión, pero no se cuentan como comportamiento malicioso confirmado.

Alto

QUICK_REFERENCE.md:133

Hidden file in home directory

## 📝 Aliases (Add to ~/.bashrc)

The skill tells users to add aliases to ~/.bashrc. Shell startup files are persistence points, even though the shown aliases appear benign.

Alto

QUICK_REFERENCE.md:133

Hidden file access

## 📝 Aliases (Add to ~/.bashrc)

The skill tells users to add aliases to ~/.bashrc. Shell startup files are persistence points, even though the shown aliases appear benign.

Alto

scripts/diagnose_voice_system.py:11

Python subprocess.run

result = subprocess.run(cmd, shell=True, capture_output=True, text=True)

The helper executes shell command strings with shell=True. Current call sites are mostly fixed, but this is still a command-execution surface.

Alto

scripts/diagnose_voice_system.py:111

Shell command substitution

print("export $(grep -v '^#' /home/adamsl/ottomator-agents/livekit-agent/.env | xargs)")

The printed export command loads every variable from a .env file through shell substitution. That can expose secrets to the shell environment.

Alto

scripts/diagnose_voice_system.py:68

Hidden file access

livekit_env = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/diagnose_voice_system.py:69

Hidden file access

planner_env = Path("/home/adamsl/planner/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/diagnose_voice_system.py:111

Hidden file access

print("export $(grep -v '^#' /home/adamsl/ottomator-agents/livekit-agent/.env | xargs)")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/diagnose_voice_system.py:72

Generic API/secret keys

livekit_vars = ["LIVEKIT_URL", "LIVEKIT_API_KEY", "LIVEKIT_API_SECRET", "DEEPGRAM_API_KEY"]

The code handles named API keys or secrets for LiveKit, Deepgram, or OpenAI. These values are credentials and require explicit handling safeguards.

Alto

scripts/diagnose_voice_system.py:81

Generic API/secret keys

if check_env_var(planner_env, "OPENAI_API_KEY") or check_env_var(livekit_env, "OPENAI_API_KEY"):

The code handles named API keys or secrets for LiveKit, Deepgram, or OpenAI. These values are credentials and require explicit handling safeguards.

Alto

scripts/generate_token.py:9

Hidden file access

env_file = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:16

Python environment access

os.environ.setdefault(key, value)

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:27

Python environment access

api_key = os.environ.get('LIVEKIT_API_KEY')

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:28

Python environment access

api_secret = os.environ.get('LIVEKIT_API_SECRET')

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:27

Generic API/secret keys

api_key = os.environ.get('LIVEKIT_API_KEY')

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:28

Generic API/secret keys

api_secret = os.environ.get('LIVEKIT_API_SECRET')

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/generate_token.py:31

Generic API/secret keys

if not api_key or not api_secret:

The code handles named API keys or secrets for LiveKit, Deepgram, or OpenAI. These values are credentials and require explicit handling safeguards.

Alto

scripts/generate_token.py:36

Generic API/secret keys

token = api.AccessToken(api_key, api_secret) \

The code handles named API keys or secrets for LiveKit, Deepgram, or OpenAI. These values are credentials and require explicit handling safeguards.

Alto

scripts/start_voice_system.py:14

Python subprocess.run

result = subprocess.run(

The startup helper checks ports through shell=True and shell pipelines. The current port values are fixed, but the command-execution pattern remains risky.

Alto

scripts/start_voice_system.py:95

Python os.exec variants

os.execv(

The script replaces itself with a hardcoded local Python executable and voice-agent file. That starts external code after loading environment secrets.

Alto

scripts/start_voice_system.py:61

Hidden file access

env_file = Path("/home/adamsl/ottomator-agents/livekit-agent/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/start_voice_system.py:71

Hidden file access

planner_env = Path("/home/adamsl/planner/.env")

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/start_voice_system.py:68

Python environment access

os.environ[key] = value

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

scripts/start_voice_system.py:78

Python environment access

os.environ.setdefault(key, value)

The code references local .env files that can contain API keys and service credentials. Reading or exporting those files is sensitive behavior.

Alto

SKILL.md:41

Hardcoded IP address

nohup ./livekit-server --dev --bind 0.0.0.0 > /tmp/livekit.log 2>&1 &

The command binds LiveKit to 0.0.0.0, which listens on all interfaces. That can expose a local dev service beyond localhost.

Medio

QUICK_REFERENCE.md:98

Temp directory access

rm -f /tmp/letta_voice_agent.{pid,lock}

The command deletes predictable files under /tmp that are used for PID and lock state. Removing those files can bypass duplicate-process protection.

Medio

scripts/diagnose_voice_system.py:89

Hidden file access

venv_python = "/home/adamsl/planner/.venv/bin/python3"

The script uses a hardcoded hidden virtualenv path to execute local Python code. This is not portable and can run unexpected local binaries.

Medio

scripts/start_voice_system.py:96

Hidden file access

"/home/adamsl/planner/.venv/bin/python3",

The script uses a hardcoded hidden virtualenv path to execute local Python code. This is not portable and can run unexpected local binaries.

Medio

scripts/start_voice_system.py:97

Hidden file access

["/home/adamsl/planner/.venv/bin/python3", LETTA_VOICE_AGENT_EXE, "start"]

The script uses a hardcoded hidden virtualenv path to execute local Python code. This is not portable and can run unexpected local binaries.

Medio

SKILL.md:41

nohup (background persistent process)

nohup ./livekit-server --dev --bind 0.0.0.0 > /tmp/livekit.log 2>&1 &

The reset workflow starts LiveKit as a persistent background process. This can leave a service running after the user expects debugging to end.

Medio

SKILL.md:44

Hidden file access

/home/adamsl/planner/.venv/bin/python3 letta_voice_agent.py dev > /tmp/letta_voice_agent.log 2>&1 &

The package references hidden local paths in commands or configuration. In a marketplace skill, those paths need explicit user review.

Medio

SKILL.md:41

Temp directory access

nohup ./livekit-server --dev --bind 0.0.0.0 > /tmp/livekit.log 2>&1 &

The workflow writes service logs to predictable files under /tmp. Shared temporary paths can create disclosure or tampering risk.

Medio

SKILL.md:44

Temp directory access

/home/adamsl/planner/.venv/bin/python3 letta_voice_agent.py dev > /tmp/letta_voice_agent.log 2>&1 &

The workflow writes service logs to predictable files under /tmp. Shared temporary paths can create disclosure or tampering risk.

Factores de riesgo

📁 Acceso al sistema de archivos (32)

🌐 Acceso a red (6)

README.md:48 scripts/generate_token.py:57 scripts/start_voice_system.py:85 SKILL.md:53 SKILL.md:41 SKILL.md:74

⚙️ Comandos externos (22)

🔑 Variables de entorno (16)

Auditado por: codex Ver historial de auditorías →

Compartir y citar este informe

Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.

Abrir el informe versionado

Copiar enlace del informe

https://skillstore.io/skills/egadams-voice-agent-expert/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Insignia Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/egadams-voice-agent-expert/security.svg)](https://skillstore.io/skills/egadams-voice-agent-expert?utm_source=security_passport_badge)

Insignia HTML

<a href="https://skillstore.io/skills/egadams-voice-agent-expert?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/egadams-voice-agent-expert/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Tarjeta para insertar

<iframe src="https://skillstore.io/embed/skills/egadams-voice-agent-expert.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Citas académicas (APA · BibTeX · CFF)

Cita APA

EGAdams. (2026). voice-agent-expert security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/egadams-voice-agent-expert/audits/8

Cita BibTeX

@techreport{egadams-egadams-voice-agent-expert-2026,
  author = {EGAdams},
  title = {voice-agent-expert security audit report (audit version 8)},
  institution = {Skillstore},
  year = {2026},
  number = {8},
  url = {https://skillstore.io/skills/egadams-voice-agent-expert/audits/8},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "voice-agent-expert security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
  - name: "EGAdams"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/egadams-voice-agent-expert/audits/8"
identifiers:
  - type: other
    value: "skillstore:egadams-voice-agent-expert:audit:8"
    description: "Skillstore immutable audit report identifier"

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Corregir la configuración local de chat de voz

Diagnosticar por qué una sesión local de voz con LiveKit y Letta no se conecta o no responde.

Depurar cortes de audio

Rastrear fallos intermitentes de audio hasta workers duplicados, salas obsoletas o un modo de agente incorrecto.

Preparar runbooks de soporte

Convertir fallos repetidos de LiveKit y Letta en comprobaciones repetibles y pasos de escalamiento.

Prueba estos prompts

Diagnosticar un fallo de conexión

Mi agente de voz LiveKit y Letta no se conecta. Pide el error y luego guíame primero por las comprobaciones más seguras.

Elegir el modo de agente correcto

Explica si debo usar el modo START o el modo DEV para el chat de voz local, y enumera los síntomas de elegir el modo incorrecto.

Investigar workers duplicados

Ayúdame a determinar si workers de voice-agent duplicados o salas LiveKit obsoletas están causando cortes de audio.

Diseñar un flujo de inicio más seguro

Revisa mi flujo local de inicio de LiveKit y Letta en busca de riesgos de seguridad, manejo de secretos y gestión de procesos más segura.

Mejores prácticas

Revisa cada comando antes de ejecutarlo contra servicios locales o archivos de inicio de shell.
Mueve las rutas codificadas de forma fija a la configuración antes de compartir este flujo de trabajo entre máquinas.
Trata los tokens de LiveKit generados y el contenido de .env como credenciales sensibles.

Evitar

No ejecutes comandos amplios para terminar procesos sin confirmar los procesos coincidentes.
No vincules servicios de desarrollo local a todas las interfaces sin controles de red.
No pegues tokens generados ni salida derivada de .env en informes públicos de incidencias.