url-to-markdown

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime script (scripts/url_to_md.sh) and SKILL.md/README explicitly fetch and extract content from arbitrary public URLs using requests/trafilatura and convert that untrusted, user-generated web content into markdown that the agent is expected to read/use as context, allowing indirect prompt injection.