background-removal

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • REMOTE_CODE_EXECUTION (HIGH): The Quick Start section contains the command curl -fsSL https://cli.inference.sh | sh. This pattern downloads a script from a remote URL and immediately executes it in the user's shell without any verification or integrity checks. This is a classic vector for arbitrary code execution.
  • COMMAND_EXECUTION (MEDIUM): The skill defines allowed-tools: Bash(infsh *), which grants the AI agent the ability to run any subcommand associated with the infsh binary. This broad permission increases the potential impact if the agent is manipulated into running malicious subcommands.
  • EXTERNAL_DOWNLOADS (LOW): The skill documentation suggests using npx skills add inference-sh/skills@..., which triggers the download and installation of additional code packages from external registries.
  • DATA_EXPOSURE (LOW): The skill sends image URLs and text prompts to an external API (inference.sh) for processing. While this is the primary purpose of the skill, users should be aware that data is being shared with a third-party service.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 18, 2026, 11:18 AM