claude-code-slash-commands

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely educational, providing documentation and templates for Claude Code's slash command feature. It does not contain any executable malicious code or dangerous instructions.
  • [COMMAND_EXECUTION]: The skill documents the platform's native ability to execute shell commands using the !command syntax to provide context (e.g., git status). These patterns are presented as features for developers to implement in their own custom commands rather than as active exploits within this skill.
  • [PROMPT_INJECTION]: The documentation describes the use of positional arguments (e.g., $1, $2) and $ARGUMENTS for command parameterization. While this pattern creates a potential surface for indirect prompt injection in the commands created by a user, the skill itself provides standard usage instructions and does not attempt to bypass agent safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:49 AM
Security Audit — agent-trust-hub — claude-code-slash-commands