skills/twentyhq/twenty/create-app/Gen Agent Trust Hub

create-app

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the 'create-twenty-app' package from the npm registry.
  • [COMMAND_EXECUTION]: The skill executes shell commands to initialize and scaffold new projects.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because user-supplied strings for app names and descriptions are interpolated into shell commands. Ingestion points: project metadata fields in SKILL.md; Boundary markers: None; Capability inventory: shell execution via npx; Sanitization: directory names are filtered for lowercase/hyphens, but other metadata strings lack explicit escaping.
  • [CREDENTIALS_UNSAFE]: The skill documentation notes that credentials are saved to the sensitive file path '~/.twenty/config.json'.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 05:35 PM
Security Audit — agent-trust-hub — create-app