slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow includes processing user-provided images, which introduces a surface for indirect prompt injection where malicious instructions could be embedded in image content or metadata.
- Ingestion points: The SKILL.md file (Working with User-Uploaded Images section) instructs the agent to open and process user-supplied image files using PIL.Image.open().
- Boundary markers: There are no instructions or delimiters provided to ensure the agent ignores potential natural language instructions found within image metadata (such as EXIF tags) or visual content.
- Capability inventory: The skill possesses file-writing capabilities through the GIFBuilder.save() method in core/gif_builder.py, which utilizes imageio.imwrite() to save GIFs to the local filesystem.
- Sanitization: No sanitization, filtering, or validation of the input image's non-pixel data is implemented.
Audit Metadata