Rapport d’audit du skill
redteam Rapport d’audit.
Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation, ASR (Attack Success Rate), or "is my app safe to deploy." Outputs ASR paired with over-refusal rate and an audit document.
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
Info76
816 stars GitHub
Activité stars/forks
Info71
816 stars et 65 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
Info64
command execution surface, database surface
Disponibilité de l’installation
Validé92
npx skills add agentscope-ai/OpenJudge --skill redteam
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/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/07-redteam
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 agentscope-ai/OpenJudge --skill redteam
Dépôt
88
https://github.com/agentscope-ai/OpenJudge/tree/main/skills/eval_pipeline/07-redteam
Licence
86
Apache-2.0
Maintenance
88
2 mois depuis le dernier push
Revue IA
55
The script assumes a specific JSONL schema for attack and over-refusal rows; while documented, it could be more flexible or provide validation errors for malformed input.
Complétude README/SKILL.md
86
Usable description available
Risque de dépendances
64
command execution surface, database surface
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
71
816 stars et 65 forks; l’activité des issues n’est pas disponible dans les métadonnées actuelles
Adoption
88
816 stars GitHub
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
Avertissements
- Permission surface may require sandboxing
- Financial research output is not financial advice; require human review before any live investment decision
- The script assumes a specific JSONL schema for attack and over-refusal rows; while documented, it could be more flexible or provide validation errors for malformed input.
- The SKILL.md excerpt is truncated in the review, but the visible content is thorough; the full file likely covers all steps.
- Financial research output is not financial advice; require human review before any live investment decision.
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- 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