li-city-impression-reversal

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a content generation tool for video scripts, using a structured 'negative to positive' storytelling framework.
  • [EXTERNAL_DOWNLOADS]: The skill includes reference links to official Douyin (TikTok China) video pages. These links are used for educational purposes to demonstrate video structures and do not trigger automated code execution.
  • [DATA_EXPOSURE]: Data is handled locally through the data.csv file provided within the skill. There is no evidence of sensitive data access or unauthorized exfiltration to external servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from data.csv to populate its scripts. While this represents a data ingestion surface, the content is static marketing data and the skill provides a structured guidance process for the AI agent, which is considered a safe and standard implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 10:37 AM
Security Audit — agent-trust-hub — li-city-impression-reversal