multi-search-engine

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by fetching and processing data from 17 different search engines. Malicious instructions hosted on indexed web pages could potentially attempt to influence the agent's behavior when the search results are parsed.
  • Ingestion points: Content retrieved from external search engines (e.g., Baidu, Google, DuckDuckGo) using the web_fetch tool as illustrated in SKILL.md examples.
  • Boundary markers: The skill does not explicitly provide delimiters or warnings to the agent to treat fetched search results as untrusted content.
  • Capability inventory: The skill facilitates data retrieval via the web_fetch capability.
  • Sanitization: There are no specific instructions for sanitizing or filtering the content returned by the search engines before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:19 AM