wishpond

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to use Membrane actions (e.g., membrane action run) to fetch Wishpond data like "Form Submissions", "Promotion Entries", and landing-page visitors — user-generated, third-party content that the agent will read and which could materially influence subsequent actions or automations.