Skills
skills/tul-sh/skills/ai-image-generation/Gen Agent Trust Hub

ai-image-generation

Fail

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill encourages the use of curl -fsSL https://cli.inference.sh | sh, a dangerous pattern that executes unverified remote code with user privileges.
  • [EXTERNAL_DOWNLOADS]: The installation process involves downloading binaries from dist.inference.sh, which is not a recognized trusted domain.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool with infsh * permissions, allowing the execution of arbitrary subcommands via the CLI.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: Untrusted user input is accepted via the prompt field in the --input JSON argument of infsh commands. Boundary markers: Input is encapsulated in JSON, but the skill lacks instructions to ignore embedded directives within the data. Capability inventory: The skill utilizes Bash(infsh *) to perform image generation tasks. Sanitization: There is no evidence of input validation or sanitization before interpolation into the CLI command.
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
Mar 4, 2026, 10:48 AM