Rapport d’audit du skill
vastai-sdk Rapport d’audit.
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
Trust Score OpenAgentSkill
Trust Score OpenAgentSkill
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
Adoption GitHub
Info62
216 stars GitHub
Activité stars/forks
Info62
216 stars et 91 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Maintenance récente
Validé88
2 mois depuis le dernier push
Clarté de licence
Validé86
MIT
Complétude README/SKILL.md
Validé86
Les métadonnées incluent suffisamment de contexte d’usage et de workflow
Risque dépendances/runtime
Échoué36
command execution surface, credential or environment access
Disponibilité de l’installation
Validé92
npx skills add vast-ai/vast-cli --skill vastai-sdk
Sécurité de la commande d’installation
Validé92
Chemin d’installation standard de package ou runtime
Surface de permissions
Échoué22
secrets or environment access, shell or command execution
Preuve du dépôt
Validé86
https://github.com/vast-ai/vast-cli/tree/master/vastai_sdk
État de revue
Info66
Données de revue IA disponibles
Résultats prouvés par Agent
Info54
Pas encore de données de résultats Agent
Vérifications
Revue d’installation et d’adoption
Chemin d’installation
92
npx skills add vast-ai/vast-cli --skill vastai-sdk
Dépôt
88
https://github.com/vast-ai/vast-cli/tree/master/vastai_sdk
Licence
86
MIT
Maintenance
88
2 mois depuis le dernier push
Revue IA
55
SKILL.md grants access to the entire vastai:* Python namespace, including destructive and costly operations such as destroy_instance, delete_deployment, unlist_machine, create_instance, and cloud_copy, without explicit confirmation or safety warnings.
Complétude README/SKILL.md
86
Usable description available
Risque de dépendances
36
command execution surface, credential or environment access
Sécurité de la commande d’installation
92
Chemin d’installation standard de package ou runtime
Surface de permissions
22
secrets or environment access, shell or command execution
Activité stars/forks
62
216 stars et 91 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
68
216 stars GitHub
Avertissements
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- SKILL.md grants access to the entire vastai:* Python namespace, including destructive and costly operations such as destroy_instance, delete_deployment, unlist_machine, create_instance, and cloud_copy, without explicit confirmation or safety warnings.
- The API key can be passed as a literal in code examples, which risks secret leakage in agent logs or chat history; no guidance on key scoping or rotation is provided.
- Safe operating boundaries are not clearly defined, such as requiring user confirmation before irreversible actions or avoiding /root and / as copy destinations.
- The provided SKILL.md appears truncated/incomplete at the SSH Keys section, so some documented functionality is not fully covered.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- 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