opencode-cli

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 and reference docs (see SKILL.md and references/mcp-servers.md) explicitly configure MCP servers such as Brave Search, Perplexity Ask, GitHub, and Notion, which enable the agent to fetch and ingest untrusted public web/social/repo content that could contain instructions influencing tool use.