deepwiki

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md and references explicitly call the DeepWiki MCP (deepwiki.com) via the mcp__mcp_deepwiki__deepwiki_fetch tool to retrieve and "read the returned markdown" for repo overviews, so it ingests untrusted third‑party web content that can materially influence the agent's decisions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill calls the DeepWiki MCP (e.g., deepwiki.com) at runtime via mcp__mcp_deepwiki__deepwiki_fetch to fetch Markdown that is injected into the agent’s context and thus can directly control prompts/instructions (flagging deepwiki.com).