copernicus-perspective
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown-based instructions and documentation. It does not contain any executable scripts, shell commands, or tool definitions.
- [PROMPT_INJECTION]: The instructions define a persona ('copernicus-perspective') that encourages critical thinking and questioning of technical assumptions. It does not contain any directives to bypass AI safety filters, ignore prior instructions, or reveal system prompts.
- [DATA_EXFILTRATION]: There are no network operations (e.g., curl, wget) or attempts to access sensitive local files such as credentials or environment variables.
- [EXTERNAL_DOWNLOADS]: The documentation references the 'nuwa-skills' GitHub organization and community resources. These are documented neutrally as installation sources for the user and are not executed by the agent at runtime.
- [DYNAMIC_CONTEXT_INJECTION]: The skill definition in SKILL.md does not utilize dynamic command execution placeholders (!
command).
Audit Metadata