synthetic-search

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent (SKILL.md and references/api.md/patterns.md) and provides helpers (scripts/search.js and scripts/probe_synthetic_search.py) to call https://api.synthetic.new/v2/search and ingest result fields like "text" (including full/truncated content via --content) and URLs from arbitrary public web pages, i.e., untrusted third‑party content that the agent is expected to read and can materially influence subsequent actions.