project-development

Warn

Audited by Snyk on Mar 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's canonical pipeline explicitly acquires content from the open Web (SKILL.md "Acquire: Obtención de datos crudos (Web, DB, Files)" and references/case-studies.md "Acquire: browser-use for descargar reportes"), which the agent is expected to read/process (Process stage) and thus could allow untrusted third‑party content to influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 07:07 AM