Rapport d’audit du skill
ai-research-explore Rapport d’audit.
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow code-only or run-only exploration, passive repo analysis, verified novelty claims, or implicit experimentation.
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
484 stars GitHub
Activité stars/forks
Avertissement57
484 stars et 16 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Maintenance récente
Validé88
1 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
Validé90
Aucun indice majeur de risque de dépendance dans les métadonnées publiques
Disponibilité de l’installation
Validé92
npx skills add lllllllama/RigorPilot-Skills --skill ai-research-explore
Sécurité de la commande d’installation
Validé92
Chemin d’installation standard de package ou runtime
Surface de permissions
Avertissement50
shell or command execution, filesystem or document access
Preuve du dépôt
Validé86
https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/ai-research-explore
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 lllllllama/RigorPilot-Skills --skill ai-research-explore
Dépôt
88
https://github.com/lllllllama/RigorPilot-Skills/tree/main/skills/ai-research-explore
Licence
86
MIT
Maintenance
88
1 mois depuis le dernier push
Revue IA
55
SKILL.md references shared references under ../ai-research-reproduction/ which are not included in this submitted skill directory; if those files are not bundled or guaranteed present, the skill may not be fully operational.
Complétude README/SKILL.md
86
Usable description available
Risque de dépendances
90
Aucun indice majeur de risque de dépendance dans les métadonnées publiques
Sécurité de la commande d’installation
92
Chemin d’installation standard de package ou runtime
Surface de permissions
50
shell or command execution, filesystem or document access
Activité stars/forks
57
484 stars et 16 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
68
484 stars GitHub
Avertissements
- Permission surface may require sandboxing
- SKILL.md references shared references under ../ai-research-reproduction/ which are not included in this submitted skill directory; if those files are not bundled or guaranteed present, the skill may not be fully operational.
- The skill delegates to other skills such as explore-code, explore-run, run-train, and analyze-project but does not clarify whether they are bundled, optional, or must be installed separately.
- No explicit setup or environment requirements are documented, such as where the isolated worktree should be created or what permissions are needed for executing runs and network lookups.
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- Stars/forks activity: 484 stars, 16 forks; issue activity unavailable in current metadata
- Permission surface: shell or command execution, filesystem or document access
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
Wazuh
Wazuh - The Open Source Security Platform. Unified XDR and SIEM protection for endpoints and cloud workloads.
16K Stars · Rapport d’audit
Maigret
🕵️♂️ Collect a dossier on a person by username from 3000+ sites
33K Stars · Rapport d’audit
Nuclei
Nuclei is a fast, customizable vulnerability scanner powered by the global security community and built on a simple YAML-based DSL, enabling collaboration to tackle trending vulnerabilities on the internet. It helps you find vulnerabilities in your applications, APIs, networks, DNS, and cloud configurations.
29K Stars · Rapport d’audit