tarot-card-reader

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill instructions are limited to natural language processing and role-playing as a tarot reader. It does not contain any executable scripts, shell commands, or external dependencies.
  • [DATA_EXFILTRATION]: No network-enabled tools or commands (such as curl, wget, or fetch) are present. The skill does not attempt to send data to external servers.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found in the instructions or reference files.
  • [REMOTE_CODE_EXECUTION]: The skill relies entirely on the model's internal logic and the provided static reference files; it does not download or execute remote scripts.
  • [PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass safety filters or override system-level constraints. The 'Role Definition' and 'Key Principles' focus on maintaining a professional and ethical persona within the context of the tarot reading task.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:17 AM
Security Audit — agent-trust-hub — tarot-card-reader