longbridge-ah-premium
Pass
Audited by Gen Agent Trust Hub on May 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists solely of instructions (SKILL.md) and does not contain any executable code, scripts, or remote downloads.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
longbridgeCLI tool. As the author of the skill is 'longbridge', this represents expected vendor functionality for interacting with their own service. - [DATA_EXPOSURE]: The metadata explicitly states a
read_onlyrisk level, and the instructions are limited to retrieving publicly available financial data (premium ratios). - [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied stock symbols, it lacks any high-risk capabilities (like file writing or arbitrary network requests) that could be exploited via malicious data ingestion.
Audit Metadata