The Agent Skills Directory

SAFE (SAFE): No malicious patterns or security risks detected.
Prompt Injection: Checked for override markers, role-play injections, and system prompt extraction. None found.
Data Exposure & Exfiltration: Scripts perform local file system operations (read/write) for project scaffolding. No network operations or hardcoded credentials detected.
Obfuscation: No encoded content, zero-width characters, or homoglyphs found.
Unverifiable Dependencies: The skill suggests installing well-known, legitimate developer tools (e.g., vitest, biome, citty). No suspicious remote code execution or untrusted packages detected.
Privilege Escalation: Uses chmod to set executable permissions on the resulting CLI binary, which is appropriate for the skill's purpose. No sudo or unauthorized system modifications detected.
Persistence: No persistence mechanisms (cron, startup scripts) identified.
Dynamic Execution: Uses safe string-replacement for templating rather than dangerous eval() or exec() calls.

npx-cli