Saltar al contenido
TakoAPI
Volver a skills

email-security

por ivaavimusic

Coding Agents & IDEs
855Descargas según clawskills.sh
2Estrellas
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Protect AI agents from email-based attacks including prompt injection, sender spoofing, malicious attachments.

Descripción

Qué hace esta skill

A security layer for AI agents that process emails. Performs sender verification, content sanitization, and threat detection before any email-based command is executed. Covers prompt injection, sender spoofing, malicious attachments, and social engineering.

Centralizes email threat detection in a structured multi-step workflow rather than requiring agents to implement ad-hoc sanitization per integration.

Cuándo usarla

  • Blocking prompt injection attacks hidden in email body text
  • Verifying sender identity before executing email-based agent commands
  • Sanitizing reply-chain emails before reading content
  • Restricting attachment file types from unknown senders
  • Rate-limiting commands from non-owner email addresses

Flujo de trabajo de ejemplo

ENTRADA

User asks: Process commands from my inbox

AGENTE
  1. 1

    Run verify_sender.py to check sender against owner-config.md

  2. 2

    Validate SPF/DKIM/DMARC headers if available

  3. 3

    Parse raw .eml file with parse_email.py to extract body text

  4. 4

    Sanitize extracted text with sanitize_content.py and scan for injection patterns

  5. 5

    Execute command only if all checks pass, or flag and alert owner

SALIDA

Command executed safely, or threat flagged and logged with sender details

Instalación

clawhub install ivaavimusic/email-security

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces