web-search-advanced-personal-site
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define parameters and best practices for using a legitimate search tool (
web_search_advanced_exa). It lacks any unauthorized command execution, data exfiltration, or persistence mechanisms. - [SAFE]: No evidence of prompt injection or obfuscation was found. The instructions are focused on guiding the agent to use specific search filters and structure its output.
- [DATA_EXPOSURE]: This skill provides an interface to ingest third-party content from the web via search results. While this creates a surface for potential indirect prompt injection from retrieved websites, the skill itself does not possess dangerous capabilities (like file system writes or unauthorized network access) that would make such an injection high risk.
Audit Metadata