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

nano-banana

Fail

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute a shell script from the vendor's domain (https://cli.inference.sh) via a pipe to the shell (curl | sh).
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to run the infsh CLI for image generation and login tasks.
  • [EXTERNAL_DOWNLOADS]: The installation process downloads executable binaries from dist.inference.sh and verifies them with checksums.
  • [PROMPT_INJECTION]: The skill processes user-supplied prompts which are passed to the CLI, representing an indirect prompt injection surface.
  • Ingestion points: The prompt parameter in the JSON input to the infsh command.
  • Boundary markers: Input is structured within a JSON object.
  • Capability inventory: Bash tool permits execution of the infsh CLI.
  • Sanitization: No explicit sanitization or filtering is described in the skill.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 07:28 PM