eval
Warn
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
bashtool to execute commands (e.g.,cp -r SCAFFOLDS_DIR/<template>/* <target>/andcd <target> && git init) where<template>and<target>are derived directly from user-supplied$ARGUMENTS. The lack of sanitization instructions for these variables presents a command injection risk if a user provides a path containing shell metacharacters like;,&&, or|. - [DATA_EXFILTRATION]: The skill includes several hardcoded absolute directory paths pointing to a specific user's home directory (
C:/Users/gurusharan.gupta/Agents/Claude Code/eval). This exposes the local file system structure and personal identifying information (the username) of the author, which could be exploited or leaked if the skill is distributed or used in a multi-user environment.
Audit Metadata