company-tech-profile

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and source-routing instructions explicitly require fetching and deep-reading public web pages/PDFs and external data sources (e.g., SKILL.md steps 1–4 and references/source-routing.md and examples/fallback-example.md which cite Exa, Brave, "web" search, and Jina URL readers to read company websites, papers, and other public pages), so the agent will ingest untrusted third‑party content that can materially influence analysis and actions.