hook-builder

[Skill Scanner] Installation of third-party script detected All findings: [CRITICAL] command_injection: Installation of third-party script detected (SC006) [AITech 9.1.4] [CRITICAL] command_injection: Installation of third-party script detected (SC006) [AITech 9.1.4] [CRITICAL] command_injection: Instruction directing agent to run/execute external content (CI011) [AITech 9.1.4] [CRITICAL] command_injection: Destructive bash command detected (rm -rf, chmod 777) (CI004) [AITech 9.1.4] [CRITICAL] command_injection: Pipe-to-shell or eval pattern detected (CI013) [AITech 9.1.4] [CRITICAL] command_injection: URL pointing to executable file detected (CI010) [AITech 9.1.4] [CRITICAL] command_injection: Destructive bash command detected (rm -rf, chmod 777) (CI004) [AITech 9.1.4] [CRITICAL] command_injection: Installation of third-party script detected (SC006) [AITech 9.1.4] [CRITICAL] command_injection: Installation of third-party script detected (SC006) [AITech 9.1.4] [CRITICAL] command_injection: Pipe-to-shell or eval pattern detected (CI013) [AITech 9.1.4] This is a hook-authoring guide (not an executable package) that intentionally exposes a high-risk capability: executing arbitrary shell commands automatically on events. The guidance includes many correct security warnings and a mandatory acknowledgment & checklist, which reduces risk if followed. However, there is no programmatic enforcement of safe commands, sandboxing, or integrity checks for downloaded content, and multiple template examples (even if labeled dangerous) could be copy-pasted erroneously. As a result the artifact is legitimate in purpose but carries a moderate-to-high operational risk if users are careless or malicious. Recommendations: enforce validation of hook commands (block dangerous tokens like 'rm -rf', 'curl | bash', hardcoded credentials), require per-user opt-in for project hooks, suggest or require sandboxing (containerized execution), and add automated pre-commit checks to prevent committing project hooks with risky commands. LLM verification: This file is a guide/metadata document for a 'hook-builder' skill that helps users create Hooks which execute arbitrary commands in response to events. It responsibly emphasizes a mandatory security checklist and enumerates many risks, but it relies on human enforcement and includes unsafe example patterns (rm -rf, curl | bash, npm/pip install) that increase the chance of dangerous copy-paste misuse. The document itself contains no obfuscated or hidden malicious code, but because it enables auto