nano-banana-2
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
infshCLI tool to run image generation applications. This tool is part of the developer's official ecosystem and is limited to specific commands. - [EXTERNAL_DOWNLOADS]: The skill references the
infshCLI and theinferenceshPython SDK. Both are official resources provided by the developer and are considered safe under the vendor context. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes user-supplied text and image URLs.
- Ingestion points: Data enters the system via the
promptandimagesparameters in the command-line interface. - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided templates.
- Capability inventory: The skill can execute CLI commands via the Bash tool.
- Sanitization: No input validation or filtering of external content is specified in the skill files.
Audit Metadata