talk-stage5-script
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs standard text processing by reading input from local markdown files in a specific directory (
talks/) and writing output to the same directory. No sensitive system files or credentials are accessed. - [SAFE]: While the skill mentions an external service (Kimi), it does not perform automated network requests. Instead, it generates a text prompt for the user to manually copy and paste, which is a transparent and safe workflow.
- [SAFE]: The instructions focus on content structure and formatting for presentation design. There are no attempts at prompt injection, obfuscation, or persistence.
- [SAFE]: The skill uses only basic file operations (
Read,Write) consistent with its stated purpose of managing talk scripts and templates.
Audit Metadata