school-facilities-manager

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified. The skill is composed of markdown-based instructions and professional domain knowledge.
  • [PROMPT_INJECTION]: The system prompt and instructions adhere to the intended professional persona without any attempts to override safety filters, bypass constraints, or extract system prompts.
  • [DATA_EXFILTRATION]: No commands for network communication or access to sensitive environment variables or local credentials (e.g., .ssh, .aws) were detected.
  • [REMOTE_CODE_EXECUTION]: There are no scripts, binary executables, or commands that download and execute code from remote sources.
  • [NO_CODE]: The skill does not include any executable scripts or configuration files (like package.json or requirements.txt) that could introduce vulnerabilities or untrusted dependencies.
  • [COMMAND_EXECUTION]: The skill does not use shell commands or subprocess calls that interact with the host system's resources in a dangerous manner.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 06:23 AM