mrbeast-perspective
Pass
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses detailed persona instructions to emulate MrBeast's decision-making style. These instructions are focused on providing content strategy advice and do not attempt to bypass the underlying AI's safety protocols, extract system prompts, or override core agent behavior.
- [COMMAND_EXECUTION]: The documentation references four local utility scripts (e.g.,
fetch_youtube_subtitles.sh,analyze_titles.py) intended for analyzing video metadata and scripts. These references are limited to describing local tool capabilities and do not include instructions for executing arbitrary or malicious commands. - [DATA_EXFILTRATION]: There is no evidence of unauthorized data transmission. The skill encourages the use of standard web search tools to gather public YouTube and market data for analysis, which is consistent with its stated purpose.
- [EXTERNAL_DOWNLOADS]: The skill does not contain any instructions to download or execute code from remote, untrusted servers. No package installation commands or remote script execution patterns were found.
Audit Metadata