risk-assessment

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Data Fetching Process explicitly instructs the agent to fetch and parse public third-party sources (e.g., Step 1 — fetching 10-K filings and Step 1.4 and Step 3 — using WebSearch for "{ticker} 10-K risk factors", news, short-seller reports, and other web content), meaning the agent will ingest untrusted public/user-generated content that could carry indirect prompt-injection instructions.