The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass AI constraints or override system prompts.
[Data Exposure & Exfiltration] (SAFE): No hardcoded secrets or credentials detected. The code correctly uses environment variables (process.env.JWT_SECRET) and standard placeholders. No unauthorized network requests to external domains.
[Obfuscation] (SAFE): No encoded strings, zero-width characters, or hidden content detected.
[Remote Code Execution] (SAFE): No patterns of downloading and executing remote scripts (e.g., curl|bash).
[Persistence & Privilege Escalation] (SAFE): No commands found that attempt to modify system configuration or elevate privileges.
[Dynamic Execution] (SAFE): JSON.parse is used on incoming WebSocket data for standard processing; no dangerous eval or exec usage was identified.

websockets