web-read

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts/read.py constructs a WebIntent with WebIntentType.READ_URL from input_data["url"] and invokes WebIntelligenceRouter.execute to fetch and normalize arbitrary URLs into Markdown, meaning untrusted public web content (including user-generated pages) is ingested and returned for the agent to read and act on.