company-profiling-zhcn
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructs the user to configure MCP servers hosted on
patsnap.comandconnect.patsnap.com. These are legitimate vendor resources belonging to the author, PatSnap, and are necessary for the skill's primary function of pharmaceutical data analysis. - [SAFE]: The setup instructions include a setup command template using a placeholder for an API key (
sk-xxxxxxxxxxxx). This follows security best practices by not hardcoding credentials and instructing the user on how to manage their own keys locally. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external databases and web searches to generate reports. While this represents a standard data ingestion surface, the skill includes rigorous internal logic, self-check procedures, and strict output formatting requirements that mitigate the risk of unintended behavior from external content. This surface is inherent to the skill's intended purpose and does not present an elevated risk.
- [SAFE]: The connectivity self-check logic ensures the agent stops and guides the user if dependencies are missing, preventing the agent from guessing data or providing incorrect information in an unconfigured state.
Audit Metadata