commands-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill documents how to execute bash commands using the ! prefix and lifecycle hooks. While these are intended features of Claude Code, they enable arbitrary command execution on the host system. The documentation includes security guidance on using allowed-tools to restrict these capabilities.
  • [PROMPT_INJECTION] (LOW): The skill facilitates the creation of commands that process untrusted input via positional arguments ($1, $2) and bash command output. This establishes a surface for indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion points: Positional arguments and bash output (references/syntax-and-arguments.md). 2. Boundary markers: Absent. 3. Capability inventory: Bash, Read, and Write tools (references/frontmatter-reference.md). 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM