Security audit
Security checks across malware telemetry and agentic risk
This is a coherent Miaoda app-building integration, but it can use an API key to create, inspect, and publicly publish apps without enough confirmation and redaction guardrails.
Install only if you intend to use Miaoda and are comfortable giving the skill a Miaoda API key, sending prompts and app details to Miaoda, and potentially consuming account credits. Keep the API base URL on the official Miaoda endpoint, avoid putting secrets or private data in prompts, review history/trajectory output carefully, and require explicit approval before generating or publishing anything publicly.
app_id: str,
fetch_timeout: int = 10,
) -> Optional[str]:
"""Extract the conversationId (contextId) for an existing app by reading its trajectory.
Scans ALL trajectory events and returns the MOST RECENT (last) non-empty contextId
found, checking two paths per event:66/66 vendors flagged this skill as clean.
No suspicious patterns detected.