stitch-skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override agent behavior were found in the skill logic or the provided templates.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local files or perform unauthorized network requests. File system operations are limited to scaffolding new skill directories and writing template content.
  • [COMMAND_EXECUTION]: The skill uses local shell commands (mkdir, cp) and a Python initialization script. These commands are used appropriately for managing local project structure and do not present a risk of arbitrary command injection from untrusted sources.
  • [EXTERNAL_DOWNLOADS]: While the skill mentions a script for downloading HTML content, this operation is part of its documented workflow for interacting with the Stitch platform using user-authorized URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 02:42 AM