web-fetch-as-markdown

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to fetch arbitrary public web pages by sending target URLs to third-party conversion services (e.g., https://markdown.new/https:// and https://r.jina.ai/https://), thereby ingesting untrusted, user-generated web content that the agent will read and act on.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime fetches from external converters (e.g., https://markdown.new/, https://r.jina.ai/ and, with consent, https://markdownforagents.com/r?url=) to retrieve converted page content which is injected into the agent’s context and thus can directly control prompts/instructions.