create-legacy-command

Pass

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: SAFEPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [SAFE]: The skill's primary function is the local generation of project scaffolding and configuration files. It does not perform unauthorized network operations, exfiltrate data, or attempt to bypass system permissions.
  • [PROMPT_INJECTION]: The skill ingests user-provided names and descriptions to populate file templates, which represents a surface for indirect prompt injection. However, the risk is mitigated by the tool's intended use-case as a developer utility and the presence of evaluation criteria in evals/evals.json that specifically test the agent's ability to identify and reject malicious input such as script injections or illegal characters.
  • [REMOTE_CODE_EXECUTION]: The skill generates Python scripts (templates/execute.py.jinja) and markdown-based command logic. This code generation is handled locally using trusted templates and does not involve the download or execution of scripts from external or untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
May 24, 2026, 08:28 AM
Security Audit — agent-trust-hub — create-legacy-command