OpenAgentSkill Registry Manifest
Skill: Adversarial Robustness Toolbox
Slug: trusted-ai-adversarial-robustness-toolbox
Category: ml-automation
Description: Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Agent fit:
- Decision: 93/100 Production-ready
- Primary fit: Sports analytics
- Role: Primary pick

Supply profile:
- Track: Coding and developer agents
- Scenario: GitHub automation
- Applicable agents: Claude Code, CLI, Codex, Cursor, Python
- Maintenance: 6mo since push
- Risk: Safe to try

Trust:
- Trust score: 93/100 Production candidate
- Audit: 87/100 Safe to try

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: Trusted-AI
- Claim URL: https://www.openagentskill.com/skills/trusted-ai-adversarial-robustness-toolbox#claim-this-skill

Install:
npx skills add Trusted-AI/adversarial-robustness-toolbox

URLs:
- Web: https://www.openagentskill.com/skills/trusted-ai-adversarial-robustness-toolbox
- API: https://www.openagentskill.com/api/agent/skills/trusted-ai-adversarial-robustness-toolbox
- Install API: https://www.openagentskill.com/api/skills/trusted-ai-adversarial-robustness-toolbox/install
- Repository: https://github.com/Trusted-AI/adversarial-robustness-toolbox