No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by DataFog · Claude Skill · ★ 68
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is datafog-python safe to install? View the security audit →
# DataFog Python DataFog is a Python library for detecting and redacting personally identifiable information (PII). It provides: Fast structured PII detection via regex An offline PII firewall for AI agents: a Claude Code hook and a LiteLLM gateway guardrail (new in 4.6) Optional NER support via spaCy and GLiNER A simple agent-oriented API for LLM applications Backward-compatible and classes Agent & Gateway Firewall (4.6) DataFog 4.6 adds two ready-made enforcement points that catch PII at the moment it would leave your machine — offline, in microseconds, with matched values never echoed into logs or transcripts: Claude Code hook (): gates agent tool calls (shell commands, web requests, file writes, MCP tools) and warns the model when prompts or tool results carry PII. 70–90ms per invocation including process startup. Easiest install is the Claude Code plugin: Manual hook setup and limitations: examples/claudecodehook/. LiteLLM guardrail (): redacts or blocks PII in requests and responses at the gateway, for any LiteLLM-proxied provider. In-process (40µs per message scanned; a request clears the guardrail in well under a millisecond), no sidecar service. Setup: [examples/litellmgua
| Stars | 68 |
| Forks | 14 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 69.2050039991145/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-13 |
| Created | 2023-06-22 |
| Platforms | claude-code, python |
| Est. Tokens | ~15k |
These tools work well together with datafog-python for enhanced workflows:
Looking for a datafog-python alternative? If you're comparing datafog-python with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret reda
Describe what you want. Go home. Sandcastle ships it. 6 AI providers, EU data residency, smart failover, cost
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
繁體中文（台灣）個人資料去識別化工具，讓業務文件可以安全地送進 AI 處理 / Reversible Traditional-Chinese (Taiwan) PII de-identification for LLM
Explore other popular claude skill tools:
datafog-python is Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.. It is categorized as a Claude Skill with 68 GitHub stars.
datafog-python is primarily written in Python. It covers topics such as agent-security, ai-agents, anonymization.
You can find installation instructions and usage details in the datafog-python GitHub repository at github.com/DataFog/datafog-python. The project has 68 stars and 14 forks, indicating an active community.
datafog-python is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to datafog-python on Agent Skills Hub include NoPII, shellward, pydantic-ai-shields. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: