dev-to

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

• Third-party content exposure detected (low risk: 0.10). The skill searches dev.to articles and content via Unbrowse's API, which retrieves outsider-authored blog posts and text articles requiring the agent to actively search specific queries.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs setting up and connecting a remote Model Context Protocol server via https://unbrowse.ai/mcp/dev.to, which acts as an operational runtime dependency controlled by an unofficial third-party platform.