skills-discovery

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly queries and displays results from the public claude-plugins.dev registry (https://claude-plugins.dev/api/skills and https://claude-plugins.dev/skills) and may surface skill metadata and external source URLs (e.g., GitHub) provided by third-party authors, which the agent will read and present—exposing it to untrusted, user-generated content that could carry indirect prompt injections.