Rapport d’audit du skill

local-ai-use Rapport d’audit.

Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays on the cloud; set this workspace up to make images on my own machine — even when the user asks for no image or file in the same breath. Also use it for a single request the user wants done locally, offline, on-device, or kept private: transcribe this recording, make this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any agent harness. Use when the user wants to cut cost or tokens on image, audio, or voice API calls, or to drop DALL-E, hosted Whisper, ElevenLabs, or other paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo, kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source code; do not use it if the user is adding local AI to an app they ship.

Bloqué · BloquerRevue nécessaireGénéré 13 oct. 2026Audit heuristique des métadonnées
73
Audit
67
Confiance
69
Qualité
69
Sécurité
88
Maintain
92
Installer

Trust Score OpenAgentSkill

67
Revue manuelle

Trust Score OpenAgentSkill

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

Adoption GitHub

Info

62

332 stars GitHub

Activité stars/forks

Avertissement

57

332 stars et 30 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles

Maintenance récente

Validé

88

1 mois depuis le dernier push

Clarté de licence

Validé

86

MIT

Complétude README/SKILL.md

Validé

86

Les métadonnées incluent suffisamment de contexte d’usage et de workflow

Risque dépendances/runtime

Échoué

36

command execution surface, credential or environment access

Disponibilité de l’installation

Validé

92

npx skills add amd/skills --skill local-ai-use

Sécurité de la commande d’installation

Validé

92

Chemin d’installation standard de package ou runtime

Surface de permissions

Échoué

22

secrets or environment access, shell or command execution

Preuve du dépôt

Validé

86

https://github.com/amd/skills/tree/main/skills/local-ai-use

État de revue

Info

66

Données de revue IA disponibles

Résultats prouvés par Agent

Info

54

Pas encore de données de résultats Agent

Vérifications

Revue d’installation et d’adoption

6 Validé · 12 Revue nécessaire

Chemin d’installation

92

Validé

npx skills add amd/skills --skill local-ai-use

Dépôt

88

Validé

https://github.com/amd/skills/tree/main/skills/local-ai-use

Licence

86

Validé

MIT

Maintenance

88

Validé

1 mois depuis le dernier push

Revue IA

55

Vérifier

The description contains an ambiguous phrase: 'even when the user asks for no image or file in the same breath' could be misinterpreted as overriding explicit user requests to not generate media. This might lead to unintended behavior if the agent follows the routing rule too aggressively.

Complétude README/SKILL.md

86

Validé

Usable description available

Risque de dépendances

36

Corriger

command execution surface, credential or environment access

Sécurité de la commande d’installation

92

Validé

Chemin d’installation standard de package ou runtime

Surface de permissions

22

Corriger

secrets or environment access, shell or command execution

Activité stars/forks

57

Corriger

332 stars et 30 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles

Adoption

68

Info

332 stars GitHub

Avertissements

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • The description contains an ambiguous phrase: 'even when the user asks for no image or file in the same breath' could be misinterpreted as overriding explicit user requests to not generate media. This might lead to unintended behavior if the agent follows the routing rule too aggressively.
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Stars/forks activity: 332 stars, 30 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution

Méthode

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Comparer les options proches

Skills associés à auditer ensuite