multi-search-engine
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates web crawling by interpolating user-supplied keywords into various search engine URL templates, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: User-provided search terms are interpolated into
{keyword}placeholders within URL templates inSKILL.md(e.g.,https://www.google.com/search?q={keyword}). - Boundary markers: The skill does not define or instruct the agent to use specific delimiters or boundary markers when processing the resulting web content.
- Capability inventory: The skill examples utilize the
web_fetchtool to retrieve external data. - Sanitization: There is no mention of sanitization, filtering, or escaping for the external content fetched from search results before it is processed by the agent.
Audit Metadata