slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-uploaded images and file paths to generate animations.
- Ingestion points: Untrusted data enters the agent context through user-provided image files (e.g.,
file.png) and file paths passed to validation functions. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within image metadata or content.
- Capability inventory: The skill includes file system write capabilities via
builder.saveandimageio.imwriteincore/gif_builder.py. - Sanitization: Relies on the standard
Pillow(PIL) library for image decoding and processing, which validates file headers and formats but does not specifically sanitize metadata for potential prompt injection strings.
Audit Metadata