genviral

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

• Third-party content exposure detected (high risk: 0.90). The skill's competitor research and niche-research workflows explicitly instruct the agent to fetch and analyze public social-media/web content (e.g., docs/references/competitor-research.md and the Niche Research Mode which calls browser navigation to TikTok and trend-brief returning sample_videos), so the agent is expected to read untrusted, user-generated third‑party pages and use those findings to drive posting/strategy decisions.