google-flow-scripting

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES]: The scripts/update.py and scripts/check_update.py utilities fetch release metadata and compressed archives from the official GitHub repository (github.com/agbelemi/google-flow-scripting-skill). These downloads are verified using SHA-256 checksums before any code execution occurs.\n- [COMMAND_EXECUTION]: The package includes management scripts that utilize subprocess.run to execute internal validation tools and the regression test suite. These operations are restricted to the skill's own directory and are used exclusively for integrity verification during installation and updates.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided briefs to generate complex prompts for video generators. It incorporates a dedicated mechanical validator (scripts/validate.py) that checks for common injection vectors and 'text-bleed' artifacts, such as hex codes or technical labels appearing in generated imagery.\n- [DYNAMIC_EXECUTION]: The update script performs local verification of the downloaded package by executing the internal test suite. This process is protected by manifest verification and path traversal checks in the extraction logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 04:42 AM