Skip to content
Back to skills

Filtered Data

ASecurity

Passthrough filter agent. Calls data sub-agents, validates responses, returns only clean data.

  • 666 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added February 8, 2026
ai-agentsbash

Security analysis

A100/100

Scanned February 12, 2026

npx -y skills add majiayu000/claude-skill-registry --skill filtered-data-faisalanjum-eventtrader --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Filtered Data?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Filtered Data
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-filtered-data/badge)](https://www.skillsdirectory.com/skills/majiayu000-filtered-data)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: filtered-data
description: Passthrough filter agent. Calls data sub-agents, validates responses, returns only clean data.
allowed-tools: Skill, Bash, Read
skills: neo4j-report, neo4j-xbrl, neo4j-news, neo4j-entity, neo4j-transcript, perplexity-search
context: fork
model: sonnet
---

# FILTER PROTOCOL

Arguments: $ARGUMENTS

## Step 1: PARSE
Extract: AGENT (after --agent), QUERY (after --query), PIT (from [PIT: datetime] if present)

## Step 2: FETCH DATA
Call Skill tool: skill=AGENT, args=QUERY

## Step 3: VALIDATE (MANDATORY)
Output "[VALIDATING]" then run:
```bash
echo 'DATA_HERE' | /home/faisal/EventMarketDB/.claude/filters/validate.sh --source "AGENT" --pit "PIT"
```
Output the validation result line.

## Step 4: RETURN
- If CLEAN: Output "[VALIDATED:CLEAN]" then return data
- If CONTAMINATED: Output "[VALIDATED:CONTAMINATED]" then return error or retry

**REDACTION RULE**: When contamination detected, report ONLY the field name (e.g., "blocked due to: daily_stock"). NEVER mention, quote, or describe any values from the blocked data.

**Execute steps 1-4 in order. Show [VALIDATING] and [VALIDATED:*] markers.**

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.