ai-image-generation

Fail

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation instructs users to execute curl -fsSL https://cli.inference.sh | sh. This is a critical security risk as it downloads a script from an external, untrusted source and pipes it directly into the shell for execution, allowing for arbitrary command execution on the host system.
  • [EXTERNAL_DOWNLOADS]: The installation script, as described, downloads platform-specific binaries from dist.inference.sh. Without being part of a trusted organization or well-known service list, these downloads are considered unverified third-party content.
  • [COMMAND_EXECUTION]: The skill is designed to execute the infsh command with various arguments, including login and app run. The app run command takes JSON input which, if derived from untrusted user data, could lead to command injection or exploitation of the underlying CLI tool.
  • [EXTERNAL_DOWNLOADS]: The skill suggests using npx skills add to download and install additional skills from the inference-sh repository. This introduces a dependency chain on unverified external code which could be modified at the source.
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
CRITICAL
Analyzed
Feb 27, 2026, 02:26 PM