skill-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill requires a mandatory "Research Assistant" teammate (references/agents-teams.md — "Mandatory Research Assistant Teammate") that uses "the user's configured search and reference tools" to gather online information (e.g., API docs), so the agent will fetch and read external/public web content which can directly influence planning and subsequent tool actions.

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

• Potentially malicious external URL detected (high risk: 0.95). The skill's update command instructs running bash -c "$(curl -fsSL https://raw.githubusercontent.com/odysseyalive/claude-enforcer/main/install)", which fetches and immediately executes remote code from that URL at runtime, creating a clear remote-execution dependency.