multi-search-engine

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the web_fetch tool to programmatically interact with search engines.
  • [EXTERNAL_DOWNLOADS]: The skill fetches search result content from well-known domains, including Google, Baidu, DuckDuckGo, and WolframAlpha.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data from external search results.
  • Ingestion points: Results from 17 external search engines via web_fetch (documented in SKILL.md and references/international-search.md).
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within search results.
  • Capability inventory: Access to the web_fetch tool for retrieving web content.
  • Sanitization: Absent; the skill does not specify any validation or filtering of fetched search data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:31 PM
Security Audit — agent-trust-hub — multi-search-engine