media-fixing-and-repair

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly asks for a file path or URL (SKILL.md Step 1) and then mandates running FFprobe and parsing its output (SKILL.md Step 2 and references/diagnostics.md), which means it ingests and interprets arbitrary public/user-supplied media and metadata that directly determine subsequent tool actions.