← All skills

detecting-data-and-model-poisoning

80 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By mukul975/Anthropic-Cybersecurity-Skills (GitHub) · security · 35,906 stars · scanned at commit 54a7988

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. Use before training or deploying on third-party/user-contributed data or downloaded checkpoints, during ML supply-chain reviews, or when investigating model misbehavior tied to specific input…

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'detecting-data-and-model-poisoning' ] || [ -L ~/.agents/skills/'detecting-data-and-model-poisoning' ]; then echo 'A skill folder named detecting-data-and-model-poisoning already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/mukul975/Anthropic-Cybersecurity-Skills' "$d" && git -C "$d" checkout --quiet '54a798831d2266a3ca61ce68a7acb80b81160d57' -- 'skills/detecting-data-and-model-poisoning' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/detecting-data-and-model-poisoning' ~/.agents/skills/'detecting-data-and-model-poisoning' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'detecting-data-and-model-poisoning' ~/.claude/skills/'detecting-data-and-model-poisoning' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for mukul975/Anthropic-Cybersecurity-Skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/mukul975/Anthropic-Cybersecurity-Skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/mukul975/Anthropic-Cybersecurity-Skills/)

Score history