multi-search-engine

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the retrieval of untrusted data from the internet, which creates a surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent's context through search results fetched via the URLs defined for 17 domestic and international engines in config.json and SKILL.md.
  • Boundary markers: The documentation and examples do not include explicit boundary markers or instructions to isolate or treat fetched web content as untrusted.
  • Capability inventory: The skill provides network access capabilities by instructing the agent on how to use the web_fetch tool with specific engine parameters.
  • Sanitization: There is no evidence of sanitization or filtering of the retrieved content before it is delivered to the agent's processing context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 08:18 AM