transifex

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

• Third-party content exposure detected (low risk: 0.10). The Transifex integration skill requires interacting with cloud-based localization records and comments, but without a dedicated monitored feed or trigger workflow, general API interactions and comment retrieval require active search or item selection, presenting a low indirect prompt injection risk.

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 npm package (@membranehq/cli) from an external registry, constituting an operational dependency on a third-party tool.