youtube-thumbnail-design

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external installation script located at raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. This URL belongs to a well-known service and is used to set up the CLI tool required for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool via Bash to perform image generation. The skill's configuration limits command execution specifically to the belt tool space, adhering to the principle of least privilege.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection where untrusted data (user-provided descriptions) is interpolated into belt app run command arguments without explicit sanitization or boundary markers. However, the impact is minimal as the available capabilities are restricted to image generation commands related to the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — youtube-thumbnail-design