multi-search-engine
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of a reference guide and configuration for various search engines, including Google, Bing, Baidu, and DuckDuckGo. All included search engines are reputable and well-known technology services. The skill facilitates legitimate web search activities without suspicious code or exfiltration patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted web content from external websites, which serves as a potential surface for indirect prompt injection attacks.
- Ingestion points: Data from the internet enters the agent context via search results fetched from URLs defined in config.json and references/international-search.md using the web_fetch tool.
- Boundary markers: There are no instructions in the skill that define delimiters or safety warnings for the agent to apply when processing retrieved web content.
- Capability inventory: The skill documentation provides examples of using the web_fetch tool for network read operations to retrieve external data.
- Sanitization: The skill does not implement or recommend any sanitization or filtering of search result content before it is parsed by the agent.
Audit Metadata