convert-to-markdown

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

• Third-party content exposure detected (low risk: 0.10). The agent actively fetches and extracts content from arbitrary web pages specified by the user via URL.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing an unverified installation script from a personal GitHub repository, presenting a weak/unknown remote operational dependency.