level-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOW
Full Analysis
- [NO_CODE] (SAFE): The skill contains only documentation in Markdown format. There are no scripts (.py, .js, .sh), configuration files for package managers (package.json, requirements.txt), or executable binaries included in the skill structure.
- [DATA_EXFILTRATION] (SAFE): No network-capable commands (curl, wget, fetch) or sensitive file path references were detected in the text content.
- [COMMAND_EXECUTION] (SAFE): There are no shell commands or system-level instructions provided for the agent to execute in its environment.
- [PROMPT_INJECTION] (SAFE): The text consists of educational material about level design (hiding linearity, anticipatory play, etc.). No instructional patterns were found that attempt to bypass AI safety filters or override system prompts.
- [INDIRECT_PROMPT_INJECTION] (INFO): While the skill is intended to help the agent evaluate user-provided level designs (external content), the skill itself possesses no write or execute capabilities, limiting the risk to reasoning/display only.
Audit Metadata