leafer-ai

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to use the public LeaferJS ai-docs GitHub repository (https://github.com/leaferjs/ai-docs) and MCP tools generated from it as the primary knowledge source, meaning the agent will fetch and act on open/public third‑party content that could alter its decisions.