Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral signatures, trigger reconstruction), Cleanlab for label-quality issues, and supply-chain checks like weight-hash verification and safetensors enforcement.
Install
npx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoningnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a claude-code -gnpx skills add mukul975/Anthropic-Cybersecurity-Skills --skill detecting-data-and-model-poisoning -a codex -ggemini skills install https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git --path skills/detecting-data-and-model-poisoninggh skill install mukul975/Anthropic-Cybersecurity-Skills detecting-data-and-model-poisoninggit clone --depth 1 https://github.com/mukul975/Anthropic-Cybersecurity-Skills /tmp/mukul975__Anthropic-Cybersecurity-Skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/detecting-data-and-model-poisoning ~/.claude/skills/detecting-data-and-model-poisoning # Claude Code
cp -R /tmp/mukul975__Anthropic-Cybersecurity-Skills/skills/detecting-data-and-model-poisoning ~/.agents/skills/detecting-data-and-model-poisoning # Codex, Cursor, Gemini CLI, Copilot, OpenCode