paper-2-web

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and integrates content from the open web (e.g., "automatic logo discovery" using the Google Search API and citation/DOI hover previews that link to external sources), meaning it ingests untrusted public third-party content as part of its workflow.