medium-research

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

• Third-party content exposure detected (low risk: 0.10). The workflow searches and fetches public Medium articles via RSS tag feeds, DuckDuckGo search, and the Freedium mirror, ingesting outsider-authored content from the web.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill uses a third-party proxy mirror (freedium-mirror.cfd) as an operational runtime dependency to fetch and extract paywalled content, which has unknown, arbitrary provenance.