wildapricot

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md instructs the agent to connect to a WildApricot account via the Membrane CLI and discover/run actions (e.g., action list / action run) against resources such as "Forums" and "Pages", which are untrusted, user-generated third-party content that the agent would read and could influence subsequent actions.