open-websearch

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly uses retrieval tools such as search, fetchWebContent, and fetchGithubReadme to fetch and read public HTTP(S) pages and GitHub READMEs (see SKILL.md and references/tools.md), meaning untrusted third‑party, user‑generated web content is ingested and can influence subsequent decisions.