simple-fetch

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

• Third-party content exposure detected (high risk: 1.00). The skill accepts an arbitrary --url and uses the MCP "fetch" tool to retrieve and return the content of external URLs (see SKILL.md examples like https://example.com and https://github.com/owner/repo/README.md), which clearly exposes the agent to untrusted third-party web content that could contain indirect prompt injection.