session-prep

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • PROMPT_INJECTION (SAFE): The instructions are purely functional for tabletop RPG preparation. There are no attempts to bypass safety filters or override agent behavior.
  • DATA_EXFILTRATION (SAFE): The skill operates on local world-building data provided by the user. It does not contain network calls, and file operations are restricted to saving game notes within the user's project structure.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill processes user-generated world data (NPCs, locations). While it ingests external content, the capability is limited to formatting text for a game master. It does not execute code or perform high-risk side effects based on that data.
  • COMMAND_EXECUTION (SAFE): No subprocess calls or shell commands are present. The skill uses standard markdown templates for output.
  • EXTERNAL_DOWNLOADS (SAFE): No external dependencies, scripts, or remote assets are referenced or downloaded.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:39 AM