multi-search-engine
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for aggregating and summarizing search results from 16 different search engines using the
web_fetchtool. This process creates a vulnerability surface for indirect prompt injection, as malicious instructions embedded in external search results could influence the agent's behavior. - Ingestion points: The skill processes external data retrieved from search engine results as described in the 'Result Aggregation' step of SKILL.md and throughout the reference guides.
- Boundary markers: There are no specific instructions or boundary markers defined to prevent the agent from following instructions found within the search results.
- Capability inventory: The skill relies on the
web_fetchtool for network operations to retrieve data from external search engine domains. - Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content fetched from the web before it is organized into a search report.
Audit Metadata