nano-banana

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the 'infsh' CLI tool through the Bash tool to perform image generation and account management tasks such as 'infsh login' and 'infsh app run'.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to installation scripts hosted on GitHub (inference-sh/skills) and suggests using 'npx' to add related skills from the author's package namespace. These resources originate from the vendor's own infrastructure.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted user input and external image URLs.
  • Ingestion points: User-supplied strings for the 'prompt' parameter and external URLs for the 'images' parameter in SKILL.md.
  • Boundary markers: Input is structured as JSON within the CLI command, though no specific instructions are provided to the agent to disregard potential instructions within that data.
  • Capability inventory: The skill has the ability to execute shell commands via the Bash tool as defined in the frontmatter of SKILL.md.
  • Sanitization: There is no evidence of input sanitization or validation before interpolation into the CLI execution string.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:25 PM
Security Audit — agent-trust-hub — nano-banana