markdown-new

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

• Third-party content exposure detected (low risk: 0.10). The agent skill converts and crawls arbitrary public URLs via markdown.new, ingesting outsider-authored web content as low-risk external data.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs usage of the third-party conversion service markdown.new via hardcoded URLs, which constitutes a common/reputable unofficial operational dependency.