slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided images, which is an inherent part of its GIF creation functionality but creates an attack surface for malformed media content.
- Ingestion points: User-uploaded images are loaded using
Image.open()as described inSKILL.mdand processed incore/gif_builder.py. - Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore instructions that might be embedded in image metadata.
- Capability inventory: The skill possesses file-read capabilities via Pillow and file-write capabilities via
imageio.imwriteincore/gif_builder.py. - Sanitization: While the skill performs image resizing and color quantization (which can normalize data), it does not explicitly sanitize or strip potentially malicious metadata from processed files.
Audit Metadata