quickcreator-developer-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes the agent to untrusted third-party content via its MCP tools (e.g., "query_question_from_web" in tool-reference.md for web search and marketplace-facing calls like "get_skill" / "get_skill_file" in SKILL.md which read user-published marketplace skill files), and the workflow instructs the agent to read and act on that content (fork/update/publish), so external pages/files could contain instructions that materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The MCP is configured to run "npx @quickcreator/skill-mcp" (QC_API_URL is set to the dev API), so the agent will fetch and execute code from the npm package URL https://www.npmjs.com/package/@quickcreator/skill-mcp at runtime and the skill depends on that MCP to operate.