text-adventure-engine
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were found across the 10 threat categories. The skill behaves as a legitimate local game engine.\n- [COMMAND_EXECUTION]: The skill uses os.system solely for terminal clearing (UI), which is appropriate for its function and does not involve untrusted data interpolation.\n- [DATA_EXFILTRATION]: Local file operations are restricted to game state management. The skill does not access sensitive system files or utilize network capabilities.\n- [PROMPT_INJECTION]: The skill processes user input and a local JSON script. Ingestion points: User input in scripts/play.py and scripts/example_game.json. Boundary markers: None (local UI use case). Capability inventory: Local file read/write and terminal clear commands. Sanitization: Input for game choices is validated against numeric ranges, and save file extensions are enforced as .json.
Audit Metadata