skills-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to query and parse results from the public claude-plugins.dev registry (e.g., curl "https://claude-plugins.dev/api/skills?q=...") and follow sourceUrl links (e.g., GitHub), which are arbitrary third‑party/user-provided entries the agent will read and present—enabling indirect prompt injection.