minimax-web-search
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and usage guidelines for a web search tool. No scripts, binaries, or configuration files are included.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from the web via search results. While this represents a potential attack surface for indirect prompt injection, the skill itself does not define any exploitable capabilities or tools that could be abused by such an injection.
- Ingestion points: Web search results (titles, snippets, and organic links) processed by the agent.
- Boundary markers: None specified in the skill instructions.
- Capability inventory: None; the skill does not define or request access to any tools.
- Sanitization: None specified.
Audit Metadata