skills/magentosh/skills/nano-banana/Gen Agent Trust Hub

nano-banana

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Links to an external installation guide on GitHub for the belt CLI.
  • [COMMAND_EXECUTION]: Uses the belt command-line tool to run image generation apps.
  • [PROMPT_INJECTION]: Untrusted user prompts are passed to the CLI without sanitization or boundary markers. Ingestion points: prompt field in SKILL.md; Boundary markers: Absent; Capability inventory: Bash(belt *) in SKILL.md; Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 06:04 PM
Security Audit — agent-trust-hub — nano-banana