multi-search-engine
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates searching and fetching content from a wide range of external web sources. This creates a vulnerability surface for indirect prompt injection, where the agent might inadvertently follow instructions hidden in third-party websites or search result snippets.
- Ingestion points: Web content and search result metadata retrieved via the
web_fetchtool from external domains such asgoogle.com,baidu.com, andduckduckgo.com(found inSKILL.mdandreferences/international-search.md). - Boundary markers: The instructions do not specify the use of delimiters or provide the agent with explicit warnings to disregard instructions found within the fetched external data.
- Capability inventory: The skill uses
web_fetchto retrieve remote data from any URL generated by the search templates. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external sources before it is processed by the agent.
Audit Metadata