Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Rag Poison Ledger

ASecurity

Use quando um agente responde errado por causa de um documento RAG duvidoso e voce precisa rastrear QUAL documento causou o erro e quais respostas ja foram contaminadas. Nao use para audit geral de logs ou para armazenar historico completo de conversas.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsbashnode

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add Abner-Machado/agent-layer --skill rag-poison-ledger --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Rag Poison Ledger?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Rag Poison Ledger
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/abner-machado-rag-poison-ledger/badge)](https://www.skillsdirectory.com/skills/abner-machado-rag-poison-ledger)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: rag-poison-ledger
description: >-
  Use quando um agente responde errado por causa de um documento RAG duvidoso
  e voce precisa rastrear QUAL documento causou o erro e quais respostas ja
  foram contaminadas. Nao use para audit geral de logs ou para armazenar
  historico completo de conversas.
---

# rag-poison-ledger

Livro-razao append-only que liga documentos RAG a respostas de agentes.

## Problema

Quando um agente responde com base em documento incorreto na base RAG, nao
ha como saber: (1) qual documento causou o erro, (2) quais respostas
anteriores foram contaminadas pelo mesmo documento.

## Solucao

Um ledger JSONL com 4 comandos:

- **record** — registra uma resposta junto com os ids dos documentos que
  foram injetados no contexto dela
- **flag** — marca um documento como `poisoned` ou `incorrect`, informando
  quem marcou e por que
- **blast** — recebe o id de um documento marcado e devolve TODAS as
  respostas que usaram aquele documento, ordenadas da mais recente para
  a mais antiga
- **trace** — faz o caminho inverso: recebe o id de uma resposta e mostra
  todos os documentos que a alimentaram, com o status de cada um

## Uso

```bash
# Registrar uma resposta
node cli.mjs record ledger.jsonl resp-42 doc-a,doc-b --text "Resposta do agente"

# Marcar documento como envenenado
node cli.mjs flag ledger.jsonl doc-a poisoned alice --why "Contem dados desatualizados"

# Ver todas as respostas afetadas por doc-a
node cli.mjs blast ledger.jsonl doc-a

# Ver quais documentos alimentaram resp-42
node cli.mjs trace ledger.jsonl resp-42

# Consultar status de um documento
node cli.mjs status ledger.jsonl doc-a
```

## Armazenamento

Arquivo JSONL append-only. Linhas antigas nunca sao reescritas.
Correcoes entram como linhas novas (`type: correction`).
O status atual de um documento e derivado de flags + corrections.

## Dependencias

Nenhuma. Apenas Node.js 20+ (usa `node:fs`, `node:path`, `node:test`).

Attribution

Abner-MachadoAbner-Machado
View sourceMore from Abner-Machado →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →