ideate

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly ingests and analyzes public third-party content — e.g., "YouTube transcripts, titles, descriptions, comments" in SKILL.md Step 1 and the "Search for trending topics in the user's niche via web search" instruction in references/substack-notes-ideation.md Trending Topic Integration — and the agent is expected to read and act on that untrusted, user-generated web content to generate ideas.