company-intel

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to scrape public websites (e.g., the Step 3 call to "orth api run scrapegraph /v1/smartscraper" with website_url="https://$DOMAIN/pricing" and other API calls that retrieve company data by domain/name), so it ingests untrusted third-party web content which the agent is expected to read and use in report generation, allowing potential indirect prompt injection.