Explorium People Search
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any executable scripts or code. It defines a high-level interface for an existing internal platform function.
- [COMMAND_EXECUTION]: There is no evidence of shell command execution, subprocess spawning, or system-level access.
- [EXTERNAL_DOWNLOADS]: The skill does not attempt to download external files or execute remote scripts. It interacts solely with the internal 'explorium-search' edge function.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, bearer tokens, or sensitive credentials were found in the skill metadata or instructions.
- [PROMPT_INJECTION]: The skill defines clear input parameters for search queries. While any input field is a theoretical surface for injection, the skill does not exhibit patterns that would bypass safety guidelines or override agent behavior.
- [DATA_EXFILTRATION]: The skill manages professional contact data as part of its primary prospecting purpose. There are no patterns indicating unauthorized data extraction or transmission to non-whitelisted domains.
Audit Metadata