Rapport d’audit du skill
harness-integration-guide Rapport d’audit.
Reference guide for building new Omnigent harness integrations — covers SDK/subprocess harnesses and native harnesses as separate tracks, each with their own feature matrix, implementation patterns, and prioritized checklist.
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
Validé94
9.3K stars GitHub
Activité stars/forks
Validé93
9.3K stars et 1.4K 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
Apache-2.0
Complétude README/SKILL.md
Validé86
Les métadonnées incluent suffisamment de contexte d’usage et de workflow
Risque dépendances/runtime
Avertissement46
command execution surface, credential or environment access
Disponibilité de l’installation
Validé92
npx skills add omnigent-ai/omnigent --skill harness-integration-guide
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/omnigent-ai/omnigent/tree/main/.claude/skills/harness-integration-guide
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 omnigent-ai/omnigent --skill harness-integration-guide
Dépôt
88
https://github.com/omnigent-ai/omnigent/tree/main/.claude/skills/harness-integration-guide
Licence
86
Apache-2.0
Maintenance
88
2 mois depuis le dernier push
Revue IA
55
The SKILL.md excerpt is incomplete; the checklist and native harness sections are truncated. Full content should be verified for completeness and accuracy.
Complétude README/SKILL.md
86
Usable description available
Risque de dépendances
46
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
93
9.3K stars et 1.4K forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
88
9.3K stars GitHub
Avertissements
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The SKILL.md excerpt is incomplete; the checklist and native harness sections are truncated. Full content should be verified for completeness and accuracy.
- No explicit mention of safe handling of credentials or secrets in the skill content (though it lists auth patterns, it does not provide security guidance for implementing them).
- 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
Skills associés à auditer ensuite
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
181K Stars · Rapport d’audit
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
95K Stars · Rapport d’audit
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
181K Stars · Rapport d’audit