arquitecto-de-briefing-landing
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Yes — SKILL.md's "Ingesta y Extracción" step explicitly instructs the agent to analyze links from Instagram and Google Maps/Business (public, user-generated sources), which the agent will read and use to build prompts and drive follow-up actions, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata