ai-gameplay-pack
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Comprehensive analysis of the skill's instructions and structure reveals no malicious intent or security vulnerabilities. The skill adheres to its stated purpose of creative content generation.
- [COMMAND_EXECUTION]: The skill utilizes file system access solely for the purpose of saving the generated prompt packages to a designated local directory (
~/Downloads/调研报告/). This is a legitimate and transparent use of the agent's capabilities for productivity. - [PROMPT_INJECTION]: While the skill contains strong internal constraints (e.g., "Highest Priority Red Lines"), these are safety and quality measures designed to ensure the agent produces original content and follows technical specifications. They do not attempt to bypass system safety filters or override administrative controls.
- [DATA_EXFILTRATION]: There is no evidence of the skill accessing sensitive files (such as credentials or SSH keys) or performing unauthorized network requests. All data processing is confined to the task of generating creative prompts.
- [REMOTE_CODE_EXECUTION]: The skill does not involve the installation of external packages or the execution of remote scripts. It is a text-based instruction set that does not download or run untrusted code.
Audit Metadata