seedance

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides detailed instructions for the agent to execute shell commands using the dreamina CLI tool. These operations include checking user credit balance and triggering video generation tasks. The skill documentation emphasizes that these commands must only be executed with explicit user consent and includes safety guardrails such as checking for a minimum credit balance before execution.
  • [SAFE]: The skill consists entirely of instructional Markdown files, prompt templates, and case studies. It does not contain any executable scripts, hardcoded credentials, or obfuscated code. The recommended installation method via directory copying is standard for AI agent skills.
  • [DATA_EXPOSURE]: No sensitive data exposure was detected. The shell commands used for CLI interaction are restricted to functional tasks within the legitimate tool's ecosystem and do not access system secrets or private keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:39 PM
Security Audit — agent-trust-hub — seedance