finding

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to query Crawlio's observation log (get_observations) and run analyze_page against hosts/pages, then create findings referencing evidence IDs from those crawled sites, which means the agent ingests and reasons over untrusted third‑party web content (crawled public pages).