skills-discovery

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to discover and read community GitHub topic pages, SKILL.md files, plugin manifests, and marketplace repos (e.g., https://github.com/topics/claude-code-plugin and other code-search targets), which are public, user-generated sources that the agent would ingest and interpret.