archaeological-drawing
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill consists entirely of markdown documentation and YAML configuration for an AI agent's behavior.
- [NO_CODE]: The skill does not include any scripts or executable files (Python, JavaScript, or shell scripts). All logic is implemented via natural language instructions and prompt templates.
- [DATA_EXFILTRATION]: No network operations (e.g., curl, wget, fetch) or sensitive file access patterns (e.g., .ssh, .aws, .env) were found in the instructions.
- [PROMPT_INJECTION]: No bypass or override markers were detected. The instructions include defensive constraints, such as the 'Calibration Gate' and 'Output Tiers', which are designed to limit the agent's output based on provided evidence rather than bypassing safety protocols. It specifically guards against misinterpreting artifact inscriptions as instructions by treating them as geometric shapes.
- [EXTERNAL_DOWNLOADS]: The skill does not attempt to install external packages or execute remote code.
Audit Metadata