slack-gif-creator

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided images, which serves as an indirect prompt injection surface. Ingestion points: SKILL.md describes loading user-uploaded images using Image.open() for processing. Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within visual data. Capability inventory: The skill has file-write capabilities via GIFBuilder.save() in core/gif_builder.py. Sanitization: No sanitization or validation of image content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill requires standard Python packages including pillow, imageio, and numpy as specified in requirements.txt. These are well-known libraries fetched from the official Python Package Index (PyPI).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 02:33 AM
Security Audit — agent-trust-hub — slack-gif-creator