tavily

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

• Third-party content exposure detected (high risk: 0.90). The skill's script (scripts/tavily_search.py) sends queries to the Tavily REST API (https://api.tavily.com/search) and the README/SKILL.md describe returning "answer" and optional "raw content" from web search results, so the agent ingests untrusted, public third‑party webpage content that can influence its summaries and decisions.