google-search

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

• Third-party content exposure detected (high risk: 0.90). This skill (SKILL.md and scripts/search.py) calls Google's Custom Search API (https://www.googleapis.com/customsearch/v1) to fetch and ingest search results from arbitrary public webpages, which the agent will read and could allow untrusted, user-generated content to influence its decisions.