hooks-mastery

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly discovers and loads third‑party plugin hook configurations from locations like ~/.claude/plugins/marketplaces/*/.../hooks/hooks.json and user/project .claude/settings.json and then executes command- and prompt-based hooks (with filesystem/network access) whose stdout/JSON responses are parsed and acted on to allow/deny/modify tool calls and agent flow, so untrusted plugin or web content can indirectly inject instructions.