playlet-xiaohongshu-feed

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local Python script fetch_playlet_feed.py to retrieve data. This script uses Python's built-in urllib library to make HTTP requests and does not perform any unsafe system calls or process unvalidated user input as shell commands.
  • [DATA_EXFILTRATION]: Network communication is restricted to doubaoya.com, which is the declared service provider for this skill's functionality. The skill uses the DOUBAOYA_API_KEY environment variable for authentication, ensuring that sensitive credentials are not hardcoded or exposed in logs.
  • [PROMPT_INJECTION]: The skill processes note titles and metrics from an external source. While this represents a surface for indirect prompt injection, the agent is instructed to use the data for structured reporting (Markdown tables and clustering), which significantly limits the potential for malicious instructions to influence the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 05:47 PM
Security Audit — agent-trust-hub — playlet-xiaohongshu-feed