copilotkit-debug

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to query external documentation and community sources—e.g., the "Using mcp-docs for Live Documentation Lookups" section (calling the copilotkit-docs MCP server / docs.copilotkit.ai) and the "Escalation Path" recommendation to search public GitHub issues and Discord—which are open/public, user-generated sources the agent is expected to read and act on for debugging decisions, creating a vector for indirect prompt injection.