mrbeast-perspective
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides utility scripts in the
scripts/directory for analyzing video content. These scripts perform standard file reading and pattern matching operations using Python and Shell commands to audit content metadata. - [EXTERNAL_DOWNLOADS]: The
fetch_youtube_subtitles.shscript downloads subtitles from YouTube using the well-knownyt-dlputility. It also includes an automated installation routine foryt-dlpfrom the official PyPI registry if the tool is not found locally. These operations are transparent and target well-known services. - [SAFE]: The persona configuration in
SKILL.mdestablishes a role-play environment for content advice. There are no instructions that attempt to override safety filters, extract system prompts, or manipulate the agent's core behavior beyond the stated persona. - [SAFE]: Analysis of the provided scripts shows that they process user-supplied text and URLs strictly for the intended purpose of content evaluation. No sensitive file access (e.g., credentials or SSH keys) or unauthorized data exfiltration patterns were found.
Audit Metadata