slack-gif-creator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's implementation is transparent and restricted to its stated purpose of image generation and validation. No patterns of credential theft, unauthorized system access, or malicious persistence were found.
  • [EXTERNAL_DOWNLOADS]: The skill requires common, reputable Python libraries to perform image manipulation tasks.
  • Evidence: requirements.txt specifies pillow, imageio, imageio-ffmpeg, and numpy.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided descriptions and emoji requests to generate frames and render text, which represents a surface for indirect prompt injection.
  • Ingestion points: User descriptions used for animation parameters and text rendering instructions in SKILL.md.
  • Boundary markers: None defined; the tool acts as a internal library for the agent.
  • Capability inventory: Limited to local image generation and GIF file saving (core/gif_builder.py). No network, shell execution, or high-privilege tools are present.
  • Sanitization: No filtering is performed on user input strings before they are rendered into GIF frames.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:29 AM
Security Audit — agent-trust-hub — slack-gif-creator