Skip to content
Agentmart
Submit a tool

data-poisoning-auditor

Scans AI training data pipelines and datasets to detect bias, data poisoning, label corruption, and statistical anomalies that could compromise autonomous AI…

Skill by smartrus

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/smartrus-data-poisoning-auditor

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Scans AI training data pipelines and datasets to detect bias, data poisoning, label corruption, and statistical anomalies that could compromise autonomous AI decision-making. Generates audit reports with poisoning risk scores and remediation recommendations. Trigger when: data poisoning, training data audit, dataset bias, label corruption, data integrity check, poisoned data detection, training pipeline audit, adversarial data, dataset contamination. Do NOT trigger: general data quality profiling without AI/ML context, RAG evaluation (use agentic-rag-evaluator), model performance evaluation, feature engineering, or data visualization.

Use cases: data, ml, security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/data-poisoning-auditor

What's inside

Skill name
data-poisoning-auditor
Description
Scans AI training data pipelines and datasets to detect bias, data poisoning, label corruption, and statistical anomalies that could compromise autonomous AI decision-making. Generates audit reports with poisoning risk scores and remediation recommendations. Trigger when: data poisoning, training data audit, dataset bias, label corruption, data integrity check, poisoned data detection, training pipeline audit, adversarial data, dataset contamination. Do NOT trigger: general data quality profiling without AI/ML context, RAG evaluation (use agentic-rag-evaluator), model performance evaluation, feature engineering, or data visualization.
License
MIT
Instructions
1 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • evals.json · evals/
  • poisoning_detector.py · scripts/

Read SKILL.md on GitHub

More from smartrus/claude-skills-and-apps

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 23, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/smartrus/claude-skills-and-apps
Website
smartrus.github.io/claude-skills-and-apps/
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from smartrus

Cite this page

data-poisoning-auditor skill. Agent Mart. https://agentmart.dev/skills/smartrus-data-poisoning-auditor (last updated 2026-10-24)