dan-koe

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

• Third-party content exposure detected (high risk: 0.85). The skill explicitly instructs the agent/user to ingest and analyze arbitrary external content such as YouTube transcripts, newsletters, landing pages and other public web content (see skills/ai-usage/SKILL.md and skills/advertising/SKILL.md where it tells users to "paste transcript" or "paste into AI" to break down third‑party pages), which are untrusted public sources the agent would read and interpret as part of its workflow.