manage-slash-commands

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the !command syntax for dynamic context in slash commands. It correctly identifies security implications and recommends using allowed-tools to restrict bash execution to specific command patterns.
  • [PROMPT_INJECTION]: The skill describes how to handle user-provided input through the $ARGUMENTS variable. It promotes the use of XML structural tags to provide clear boundaries and reduce the risk of the model misinterpreting user input as system instructions.
  • [SAFE]: Documentation examples use standard development tools like git, npm, and gh. The skill explicitly discusses security patterns to block dangerous operations like arbitrary shell execution or network requests using platform-native restriction mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 11:38 AM