claude-code

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md and docs explicitly instruct the agent to fetch and read external URLs (e.g., "Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt" in docs/agent-teams.md), to use the plugin marketplace and install community plugins, and to connect MCP servers (Notion, Figma, databases) so the agent will ingest and act on open/public third‑party content that can change tool availability and drive follow-up actions.