reviewsio

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the skill uses the Membrane CLI to run actions and proxy requests against Reviews.io (see "Popular actions", "Running actions", and "Proxy requests"), which fetches user-generated reviews from a public third-party site so the agent would read and act on untrusted third-party content.