video-script
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses tools like WebFetch and the GitHub API (
gh api) to retrieve live data from external URLs and software repositories for verification purposes. - [DATA_EXPOSURE]: It reads from local state files such as
memory/MEMORY.mdandsoul/SOUL.mdto ensure script consistency and maintain a specific persona. - [COMMAND_EXECUTION]: The skill utilizes local shell operations for file management (
mkdir -p, redirection) and triggers a local notification script (./notify). - [INDIRECT_PROMPT_INJECTION]: As the skill ingests data from untrusted external sources (websites and public repositories), it is theoretically susceptible to indirect prompt injection. However, its primary function is summarizing and formatting, which minimizes the risk of harmful outcomes.
Audit Metadata