deep-post-ideas

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests and analyzes arbitrary "reference material" provided by the user (see "Use when the user provides reference material" and "From the user's input, identify:"), which means the agent will read untrusted/user-generated third‑party content as part of its workflow and could be exposed to indirect prompt injection.