china-macro-analyst
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to override model behavior or ignore previous guidelines.- [Data Exposure] (SAFE): No hardcoded credentials, API keys, or access to sensitive local file paths were found.- [Remote Code Execution] (SAFE): There are no commands or patterns indicating remote script execution or external downloads.- [Indirect Prompt Injection] (LOW): The skill is designed to process external economic data from search results. This constitutes an attack surface; however, the skill has no capability to execute code, write files, or perform network requests, limiting potential impact to the generated text.- [Dynamic Execution] (SAFE): No logic exists for runtime code generation or unsafe data deserialization.
Audit Metadata