What makes TrustBoost PII Sanitizer notable?

1.3K downloads. Trust evidence available

How should TrustBoost PII Sanitizer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

TrustBoost PII Sanitizer

Context-aware PII sanitization for autonomous AI agent pipelines. Sanitizes text before LLMs with 5 context modes (legal/financial/medical/code/general), Pri...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

2.0.7

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 2.0.7release · observed Jun 17, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s174f8wsyybamj8bhwkwa7y5fh85h9zs:trustboost-pii-sanitizer

Install using `clawhub skill install s174f8wsyybamj8bhwkwa7y5fh85h9zs:trustboost-pii-sanitizer` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/teodorofodocrispin-cmyk/trustboost-pii-sanitizer before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-teodorofodocrispin-cmyk-trustboost-pii-sanitizer/snapshot"

Documentation

CLAWHUB

122,671 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: trustboost-pii-sanitizer
version: "2.6.0"
description: Context-aware PII sanitization for autonomous AI agent pipelines. Sanitizes text before LLMs with 5 context modes (legal/financial/medical/code/general), Privacy Budget per agent, and TrustBoost Score for M2M trust verification. Supports EN, ES (LATAM), PT (BR/PT), DE, JA, FR, IT, KO with country-specific patterns (RFC, CUIT, CPF, CNPJ, Personalausweis, マイナンバー, NIR, Codice Fiscale, 주민등록번호). Returns sanitized text, safety_score (0.0-1.0), risk_category (CRITICAL/PRIVATE/SENSITIVE/CLEAN), and context_applied. No SDK required — single POST request. 50 free requests per wallet with tx_hash="TRIAL".
license: MIT
compatibility: Requires internet access to reach the TrustBoost API. No local dependencies. Compatible with any agent that can make HTTP POST requests. No authentication required.
metadata:
  author: teodorofodocrispin-cmyk
  version: "2.6.0"
  endpoint: https://api.trustboost.dev/sanitize
  health: https://api.trustboost.dev/health
  payment: Solana USDC (149 USDC = 10,000 sanitizations)
  trial: tx_hash=TRIAL (50 free sanitizations per wallet, no payment required)
  preview: https://api.trustboost.dev/sanitize/preview (3 free requests per IP, no wallet required)
  autonomy_score: 8.5/10
  audit_score: 9.8/10
  languages: English, Spanish, Portuguese, German, Japanese, French, Italian, Korean
  compliance: GDPR, LGPD, APPI, CCPA, DPDPA
  requires_env: none
  wallet_security: >
    TrustBoost NEVER requires wallet private keys, seed phrases, or signing credentials.
    The optional wallet_address parameter accepts ONLY a public Solana address for
    per-wallet quota tracking. Payment signing happens entirely client-side — TrustBoost
    only verifies the resulting tx_hash on-chain via Helius oracle. No private key
    ever touches TrustBoost infrastructure.
  infrastructure: FastAPI + Supabase + Render (AWS)
  features:
    - context_aware_sanitization (legal/financial/medical/code/general)
    - privacy_budget_per_agent (configurable daily limits)
    - trustboost_score (M2M trust verification)
  mcp_server: https://api.trustboost.dev/mcp
  homepage: https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer
---

> ⚠️ **Data Handling Notice:** TrustBoost sends text to a remote API (api.trustboost.dev) for sanitization. Raw input is transmitted over HTTPS, processed, and immediately discarded — it is never stored or logged. Only sanitized output and metadata are retained (90 days). Review [PRIVACY.md](./PRIVACY.md) before submitting regulated records, credentials, or customer data. Use `/sanitize/preview` for a zero-retention free test.


# TrustBoost PII Sanitizer v2.6.0

A blockchain-verified privacy layer that redacts PII from text before it reaches LLMs or external services. Payment is verified trustlessly on Solana via Helius oracle — no API key, no SDK, no human intervention required.

Running on FastAPI + Supabase + Render (AWS) — production-grade infrastructure

_meta.json

{
  "ownerId": "kn737t0byp849ayr51k6ac39sn85gqjr",
  "slug": "trustboost-pii-sanitizer",
  "version": "2.0.7",
  "publishedAt": 1781664372152
}

skill-card.md

## Description:

Context-aware PII sanitization for autonomous AI agent pipelines that sends text to the TrustBoost API, redacts detected PII across supported languages, and returns sanitized text with safety and risk metadata.

This skill is ready for commercial/non-commercial use.

## Publisher:

[teodorofodocrispin-cmyk](https://clawhub.ai/user/teodorofodocrispin-cmyk)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent builders use this skill to sanitize user-generated or workflow text before sending it to LLMs or external services. It is intended for multilingual privacy-risk reduction where a remote third-party API is acceptable.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Raw input is transmitted to a third-party remote API before sanitization.

Mitigation: Install only where third-party processing is approved; do not send secrets, private keys, passwords, regulated records, or zero-transmission workloads without separate contractual and technical controls.

Risk: The skill includes autonomous cryptocurrency payment guidance.

Mitigation: Do not grant agents wallet-signing authority or automatic USDC payment capability through this skill; handle billing manually or through a separately approved payment workflow.

Risk: Sanitization may not remove every sensitive value in adversarial or high-risk inputs.

Mitigation: Review sanitized output before downstream use in sensitive workflows and treat the service as risk reduction rather than a complete data-loss-prevention control.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/teodorofodocrispin-cmyk/skills/trustboost-pii-sanitizer)
- [TrustBoost API Endpoint](https://api.trustboost.dev/sanitize)
- [TrustBoost Preview Endpoint](https://api.trustboost.dev/sanitize/preview)
- [TrustBoost MCP Server](https://api.trustboost.dev/mcp)
- [GitHub Repository](https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer)
- [Agent Evaluation Report](https://github.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/blob/main/AGENT_EVALUATION.md)
- [MOLT Schema](https://raw.githubusercontent.com/teodorofodocrispin-cmyk/TrustBoost-PII-Sanitizer/main/molt.json)
- [Live Demo](https://huggingface.co/spaces/TrustBoost/pii-sanitizer)

## Skill Output:

**Output Type(s):** [Text, JSON, Shell commands, Guidance]

**Output Format:** [Markdown guidance with curl examples and JSON request/response payloads; runtime API responses are JSON.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires internet access to TrustBoost API; paid use may involve Solana USDC transaction fields.]

## Skill Version(s):

2.0.7 (source: server release metadata; artifact frontmatter declares 2.6.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requir

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular