short-form-converter

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and analyzes arbitrary user-provided media and text — e.g., the "From Video File" and "From Transcript" sections where users paste transcripts or supply videos — which can contain untrusted, third-party/user-generated content that the agent will read and interpret.