repomix

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [External Downloads] (MEDIUM): The skill requires installing the repomix CLI tool via npm install -g repomix. While repomix is a known utility for this purpose, it originates from an external source not included in the designated trusted organizations list.
  • [Command Execution] (LOW): The core functionality of the skill involves executing CLI commands through the repomix binary to analyze file structures and generate consolidated context files.
  • [Prompt Injection] (LOW): This skill presents an Indirect Prompt Injection surface (Category 8) by ingesting and formatting untrusted codebase data for AI consumption.
  • Ingestion points: Processes local file paths and remote repository URLs via the --remote flag.
  • Boundary markers: Supports XML, Markdown, and JSON formatting which provide structural delimiters for file content.
  • Capability inventory: The skill executes shell commands and potentially writes aggregate repository data to files or the clipboard.
  • Sanitization: Uses Secretlint by default to detect hardcoded secrets; however, it lacks specific sanitization for malicious instructions or hidden patterns embedded in the analyzed code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM