wechat-viral-topic
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any malicious instructions or prompt injection patterns. Its purpose is clearly defined and consistent with its implementation.
- [SAFE]: No hardcoded credentials were found. The skill correctly instructs users to manage API keys via environment variables, and the provided script includes logic to redact these values in logs to prevent accidental exposure.
- [SAFE]: The Python script relies entirely on standard libraries (argparse, urllib, json, etc.) and does not download or execute external code at runtime.
- [SAFE]: Network operations are directed to a user-provided API base for legitimate data retrieval. No signs of data exfiltration to unknown or malicious domains were detected.
- [SAFE]: Indirect prompt injection risk was evaluated. The skill ingests external article titles from the WeChat API (ingestion point: scripts/search_wechat_viral_topic.py); however, as a data ranking and retrieval tool with no command-execution capabilities (capability inventory: network reads only), the risk of executing instructions embedded in titles is negligible.
Audit Metadata