skills/inf-sh/skills/nano-banana/Gen Agent Trust Hub

nano-banana

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs users to install a CLI tool using a script from cli.inference.sh. This script is provided by the vendor (inf-sh) to facilitate tool setup.
  • [EXTERNAL_DOWNLOADS]: Binaries for the infsh tool are downloaded from dist.inference.sh as part of the installation process.
  • [COMMAND_EXECUTION]: The skill executes the infsh CLI to perform image generation tasks, which is the core functionality of the skill.
  • [PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection as it processes user-provided prompt strings. 1. Ingestion points: The --input parameter in SKILL.md. 2. Boundary markers: Input is structured as JSON. 3. Capability inventory: The skill executes the infsh command. 4. Sanitization: No sanitization is implemented in the skill markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:10 PM
Security Audit — agent-trust-hub — nano-banana