mercado-libre

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

• Third-party content exposure detected (medium risk: 0.30). The skill integrates with Mercado Libre via the Membrane CLI, allowing the agent to read marketplace records and interact with APIs where untrusted user-generated content or listings may be consumed, presenting a medium risk of indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an external CLI tool (@membranehq/cli) from npm, which constitutes an operational dependency without strong official provenance.