grab-your-reviews

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and list user-generated reviews and other data from the Grab Your Reviews API (see "Popular actions" -> "List Reviews" and the "Proxy requests" section in SKILL.md), which are untrusted third-party contents that the agent is expected to read and could materially influence its actions.