lp-manga
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown prompt templates and architectural documentation. No executable scripts, binaries, or source code files are included, significantly reducing the attack surface.
- [COMMAND_EXECUTION]: The skill does not utilize any tools or instructions that execute shell commands or interact with the operating system beyond standard file management.
- [DATA_EXFILTRATION]: No network-related tools (curl, wget, etc.) or functions are present. The skill operates exclusively on local project files within the user's workspace.
- [PROMPT_INJECTION]: The prompt templates use advanced engineering techniques such as Role-Play, Chain-of-Thought (CoT), and XML-based structured formatting. No malicious overrides or safety bypass instructions were detected.
- [SAFE]: The skill implements a robust safety design by requiring explicit user confirmation and approval at the end of every phase (Requirements, Concept, Design) before proceeding to the next step.
Audit Metadata