skills/sorrycc/skills/create-skill/Gen Agent Trust Hub

create-skill

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash to create directories and write files (~/.claude/skills/ or ./.claude/skills/). This is a documented core function for skill management and does not involve unauthorized access or dangerous command injection.
  • [DYNAMIC_CONTEXT_INJECTION]: The reference.md file documents the ! <command> syntax for dynamic context injection. While this feature executes shell commands at load time, the file only serves as a reference guide for developers and does not contain any malicious pre-load commands. The examples provided (e.g., gh pr diff) are standard development workflows.
  • [PROMPT_INJECTION]: No patterns were detected that attempt to bypass safety filters or override system instructions. The instructions are focused on scaffolding and best practices for skill creation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 08:54 AM
Security Audit — agent-trust-hub — create-skill