game-code-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches and reads PR diffs and changed files via the GitHub MCP and queries/ingests engine documentation via Context7 (see "PR-Based Code Review" and "Connected MCP Servers"), meaning it routinely consumes untrusted, user-generated third-party content that the agent must interpret and act on for reviews.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs runtime connections to external MCP servers (e.g. https://github.com/Coding-Solo/godot-mcp, https://github.com/CoplayDev/unity-mcp, https://github.com/chongdashu/unreal-mcp) which are used during reviews to run engine-side code (run GDScript/inspect editor state), so these URLs enable execution of remote code relied on by the workflow.