commandbox-usage

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent on how to use the CommandBox CLI to execute shell commands, manage packages (e.g., install coldbox), and interact with the operating system using the ! prefix in aliases.
  • [DYNAMIC_EXECUTION]: The skill describes features for dynamic code evaluation, including the CommandBox REPL for CFML/BoxLang and backtick expressions that substitute command results into other commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill details workflows where the agent processes output from external commands using tools like jq, sql, and foreach.
  • Ingestion points: Data enters the context from command outputs such as package show or server list (SKILL.md).
  • Boundary markers: None identified in the provided examples.
  • Capability inventory: The skill provides access to full shell execution via the box command (SKILL.md).
  • Sanitization: No specific sanitization or filtering of external command output is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — commandbox-usage