AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/yaklang/hack-skills/main/skills/ai-ml-security/SKILL.mdRegistry
github (via claudemarketplaces.com)