hot-topic-radar

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary logic is focused on data aggregation and filtering, which aligns with its documented purpose.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from well-known services (Weibo, Toutiao, and Baidu) via their public endpoints. This is a core part of the skill's functionality and does not involve downloading executable code.
  • [COMMAND_EXECUTION]: The Python scripts (fetch_hot.py and weekly_report.py) do not use functions for executing shell commands or spawning subprocesses.
  • [DATA_EXFILTRATION]: There is no evidence of local sensitive data being transmitted to external servers. The skill only performs read operations on its own configuration and memory files.
  • [PROMPT_INJECTION]: The SKILL.md file contains clear boundaries and instructions for the agent's behavior without attempting to bypass safety protocols or perform malicious overrides.
  • [DATA_EXPOSURE]: All collected data is stored locally in the memory/ and workflow/ directories as described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 01:36 AM