skills/binjuhor/shadcn-lar/repomix/Gen Agent Trust Hub

repomix

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill guides the agent to install repomix via npm or brew and uses npx to process remote repositories. While repomix is a recognized utility, it does not originate from the specified trusted organizations.
  • [COMMAND_EXECUTION] (LOW): The skill relies on executing shell commands (repomix, npx) to perform its core functions. This is consistent with the skill's purpose.
  • [PROMPT_INJECTION] (LOW): The skill is subject to Indirect Prompt Injection (Category 8) because it ingests untrusted data from repositories. A malicious repository could contain instructions designed to subvert the LLM's behavior once the 'packed' file is processed.
  • Ingestion points: Local filesystem files and remote Git repositories via --remote flag.
  • Boundary markers: Supports XML, Markdown, and JSON formatting which provides structural delimiters.
  • Capability inventory: Executes the repomix CLI tool which has read access to the filesystem.
  • Sanitization: Includes built-in secret detection using Secretlint to filter sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 06:24 AM