mercadolivre

Warn

Audited by Snyk on Mar 1, 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 (scripts/mercadolivre.py and SKILL.md) directly fetches and parses live pages from the public site mercadolivre.com.br via Camoufox (see MercadoLivreClient.fetch_html and the cmd_search/cmd_details/cmd_reviews/cmd_sellers/cmd_shipping flows), ingesting untrusted, user-generated content such as product descriptions, seller listings and reviews which the agent interprets and uses to drive outputs and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 06:20 AM