using-claude-hooks

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.85). This content enables execution of arbitrary commands via project-committed hooks, HTTP/webhook calls with interpolated tokens, and environment access—features that can be deliberately abused for data exfiltration, credential theft, remote code execution and supply-chain/backdoor insertion if a malicious actor adds or modifies .claude settings or hook scripts.

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Advanced Topics — HTTP Hooks" shows hooks can call arbitrary external URLs (e.g., "type": "http", "url": "https://api.example.com/webhook"), and those external responses can be consumed by PreToolUse/PostToolUse hooks that block or permit operations, so untrusted third‑party content could materially influence agent behavior.