minimax
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, making it vulnerable to indirect prompt injection. 1. Ingestion points: Data enters the agent's context through search results via the 'web_search' tool and content from remote images or URLs via the 'understand_image' tool. 2. Boundary markers: The skill does not provide delimiters or instructions to the agent to treat external content as untrusted data, which could allow embedded instructions to influence agent behavior. 3. Capability inventory: The skill itself contains no executable scripts or system-level capabilities; it describes the usage of external tools. 4. Sanitization: No evidence of validation or sanitization of retrieved content is present.
- [NO_CODE]: This skill contains no executable scripts, binaries, or source code files, consisting only of documentation and tool definitions.
Audit Metadata