nano-banana

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to interact with the belt command-line interface, performing actions such as authentication and executing image generation applications as documented in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: Setup instructions in SKILL.md recommend installing the belt-sh/cli and related components via npx skills add, which downloads code from the service provider's official repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied natural language prompts which are interpolated into belt CLI commands, creating an inherent surface for indirect prompt injection.
  • Ingestion points: User-provided prompt text and image URLs used in the --input parameter throughout SKILL.md examples.
  • Boundary markers: Input parameters are encapsulated within JSON objects or single-quoted strings in the shell commands.
  • Capability inventory: Shell command execution via the Bash tool, restricted to the belt executable by the skill's frontmatter.
  • Sanitization: No explicit sanitization or input filtering is implemented within the skill instructions, relying on the platform's standard command handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:44 AM