book-cover-design

Fail

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides an installation command curl -fsSL https://cli.inference.sh | sh. This 'curl-pipe-to-shell' pattern fetches and executes a remote script with the user's local privileges, which is a significant security risk as the script's contents are not inspected before execution.
  • [EXTERNAL_DOWNLOADS]: The skill relies on external resources from inference.sh and dist.inference.sh for its core functionality. Additionally, it references external skill packages via npx skills add, which introduces unverified third-party dependencies from the npm registry.
  • [COMMAND_EXECUTION]: The skill is configured to use the Bash tool to run the infsh command-line utility. This grants the agent the ability to execute commands within the scope of that tool, which could be exploited if the tool itself contains vulnerabilities.
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, 12:29 PM