mcp-developer

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

• Third-party content exposure detected (high risk: 0.90). The skill's reference docs explicitly include runtime patterns that fetch and return arbitrary third-party content — e.g., the "HTTP API Tool" in references/tools.md uses httpx to GET args.url and return response.text, and references/resources.md shows repo:// templates that call fetchGitHubIssues(owner, repo) — which ingest untrusted, user-generated web content that could influence tool outputs and subsequent agent actions.