web-debug-search
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill incorporates strong data handling practices by instructing the agent to redact credentials, tokens, and private URLs from user-provided arguments before initiating web searches.
- [SAFE]: The skill includes explicit defensive instructions to mitigate indirect prompt injection, warning the agent that external web content is untrusted and that it should never follow instructions found within fetched pages.
- [SAFE]: The skill's capabilities are restricted to web searching and fetching, with no access to sensitive local tools such as shell execution or file system modifications.
Audit Metadata