slack-gif-creator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted user-uploaded images and natural language instructions to generate animation frames.\n
  • Ingestion points: User-provided images are loaded using PIL.Image.open() in the 'Working with User-Uploaded Images' section of SKILL.md.\n
  • Boundary markers: No specific boundary markers or instructions are provided to separate user data from the agent's logic.\n
  • Capability inventory: The skill utilizes PIL for image manipulation and allows writing output files to the local directory via builder.save().\n
  • Sanitization: No explicit sanitization of image metadata or file content is performed beyond the default behavior of the Pillow library.\n- External Downloads (LOW): The skill requests the installation of pillow, imageio, and numpy. These are well-known, trusted packages from the standard PyPI registry; however, versions are not pinned, representing a minor security best-practice violation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 11:00 AM