China Market Localization Strategist

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation and instructions. There are no executable scripts, shell commands, or external package dependencies included.
  • [SAFE]: No hardcoded credentials, API keys, or sensitive file paths were detected. The instructions explicitly direct the agent to comply with advertising laws and content moderation rules.
  • [PROMPT_INJECTION]: The skill processes untrusted external content by monitoring social media trending topics and analyzing user comments. This introduces a surface for indirect prompt injection, which is handled at a safe level as no high-privilege tools are requested. 1. Ingestion points: Douyin, Weibo, and Xiaohongshu hotlists and comment tracks (SKILL.md). 2. Boundary markers: The instructions lack explicit delimiters for external content. 3. Capability inventory: Generation of marketing strategies, content scripts, and FAQs only. 4. Sanitization: No data sanitization steps are defined in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 05:25 AM
Security Audit — agent-trust-hub — China Market Localization Strategist