Skills
Navigate
skills/101-skills/superpowers/nano-banana/Gen Agent Trust Hub

nano-banana

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text prompts for image generation, creating a surface for indirect prompt injection.\n
  • Ingestion points: The prompt parameter in SKILL.md.\n
  • Boundary markers: None specified to delimit user input.\n
  • Capability inventory: Execution of shell commands via the belt CLI.\n
  • Sanitization: No explicit sanitization of input prompts is defined.\n- [EXTERNAL_DOWNLOADS]: The skill references and requires the installation of external tools and packages.\n
  • References installation of belt-sh/cli and inference-sh/skills packages via npx.\n
  • Links to external documentation on GitHub for installation instructions.\n- [COMMAND_EXECUTION]: The skill performs shell command execution using the belt CLI tool to run inference tasks on remote models.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:00 PM
Security Audit — agent-trust-hub — nano-banana