slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted user-uploaded images and natural language instructions to generate GIF content.
- Ingestion points: User-supplied image files and natural language instructions for GIF generation (referenced in SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions potentially embedded in processed data.
- Capability inventory: The skill utilizes file system write operations via GIFBuilder.save in core/gif_builder.py and subprocess capabilities via imageio-ffmpeg.
- Sanitization: No specific sanitization or validation of the content within uploaded images or instructions is implemented.
- [SAFE]: The skill utilizes well-known, industry-standard libraries including Pillow, Imageio, and Numpy for its core functionality. All external dependencies listed in requirements.txt are standard packages from official registries and are used according to their intended purposes.
Audit Metadata