noob-mode
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses behavioral override instructions such as "follow ALL of the rules below for the remainder of the conversation." In this context, these instructions are used to maintain a consistent user interface and tone (translating jargon and explaining risks) rather than to bypass the agent's safety guardrails.
- [SAFE]: The skill explicitly implements a risk-assessment framework (Rule 2) that identifies and explains high-risk actions like file deletion, credential modification, and remote server access to the user before execution. This is a defensive feature that promotes security awareness.
- [EXTERNAL_DOWNLOADS]: The documentation references well-known technology resources such as the 'lodash' library and 'github/docs' repository as examples in its glossary and translation rules. These are documented neutrally and do not represent a risk of unauthorized remote code execution.
- [SAFE]: No evidence of data exfiltration, obfuscation, or unauthorized persistence mechanisms was found. The skill operates as a set of instructional prompts and reference files.
Audit Metadata