Skills
skills/skillsh/skills/nano-banana/Gen Agent Trust Hub

nano-banana

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the infsh CLI tool from the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: The skill uses the infsh command-line utility to interface with image generation models.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes user-provided prompts and incorporates them into CLI commands.
  • Ingestion points: User-defined prompt strings in image generation requests (as described in SKILL.md).
  • Boundary markers: Prompts are encapsulated within a JSON structure for the CLI input.
  • Capability inventory: Accesses the infsh CLI tool via the Bash tool to perform image generation and manipulation.
  • Sanitization: No explicit sanitization or validation of the prompt content is documented within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 12:27 PM