The Agent Skills Directory

[SAFE]: The skill consists of technical documentation and code examples for implementing Server-Sent Events (SSE) using both the EventSource API and fetch streaming. Analysis of the provided TypeScript and React patterns shows no malicious intent, data exfiltration, or obfuscation.
[INDIRECT_PROMPT_INJECTION]: The skill naturally handles external data via network streams. It proactively identifies this as a security boundary in its 'Red Flags' section, advising developers to validate all payload content as it is 'attacker-influenced text'. This aligns with secure coding practices for handling untrusted input.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic execution patterns (like eval) were found in any of the analyzed files.
[CREDENTIALS_UNSAFE]: The code examples use appropriate placeholders for authentication tokens and follow standard practices by recommending the use of Authorization headers or secure cookies rather than sensitive data in URL parameters.

web-realtime-sse