skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs various system-level operations by executing shell commands. Scripts such as scripts/install_deps.js and scripts/add_dependency.js invoke the pnpm package manager via child_process.spawn. Additionally, scripts/assign_codex.js executes git and codex CLI commands using child_process.execSync to manage repository state and delegate tasks to external models.
  • [EXTERNAL_DOWNLOADS]: Through its dependency management scripts, the skill automates the fetching of software packages from the official npm registry via the pnpm tool. These actions are transparent and necessary for the self-contained nature of the skills it generates.
  • [PROMPT_INJECTION]: As a meta-tool that transforms user requirements into AI instructions, the skill handles untrusted data that could lead to indirect prompt injection. However, the skill contains explicit security documentation (references/external-cli-agents-guide.md) that instructs users on how to safely handle inputs and avoid shell injection vulnerabilities in generated scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 02:57 PM
Security Audit — agent-trust-hub — skill-creator