skills/siy/coding-technology/JBCT/Gen Agent Trust Hub

JBCT

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • REMOTE_CODE_EXECUTION (HIGH): The skill documentation (README.md) suggests verifying the installation via a CLI tool, and the metadata contains a command that pipes a remote shell script directly into the shell (curl -fsSL https://raw.githubusercontent.com/siy/jbct-cli/main/install.sh | sh). This is a classic RCE vector where a third party controls the code executed on the user's machine.
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill references an external repository (siy/jbct-cli) which is not on the trusted sources list. Downloading and executing content from unverified GitHub users poses a significant security risk.
  • COMMAND_EXECUTION (LOW): The skill README.md provides standard commands for directory creation (mkdir -p) and file copying (cp -r), which are benign in isolation but contribute to the execution of the skill's setup.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/siy/jbct-cli/main/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:42 PM