multi-search-engine
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference for constructing search queries across various platforms. All provided URL templates point to official and well-known search engines, including Google, Bing, DuckDuckGo, WolframAlpha, Brave, and several major Chinese providers (Baidu, Sogou, 360).
- [PROMPT_INJECTION]: The skill's primary function is to facilitate the ingestion of external web content into the agent's context via the web_fetch tool. This constitutes an indirect prompt injection attack surface, as the agent might process instructions or malicious content contained within the fetched search results. However, this is an inherent and expected risk of any web-searching functionality.
- [SAFE]: No hardcoded credentials, malicious remote code execution patterns, or obfuscated contents were found within the documentation or reference files.
Audit Metadata