slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains legitimate code for image animation, color quantization, and frame optimization. The dependencies and implementation are consistent with the stated purpose of creating Slack GIFs.
- [INDIRECT_PROMPT_INJECTION]: The skill has a standard attack surface for indirect prompt injection because it processes user-provided images and text strings.
- Ingestion points: Untrusted data enters the agent context via user-uploaded images (processed in
SKILL.mdandcore/gif_builder.py) and user-supplied text strings rendered into frames usingdraw_textincore/frame_composer.py. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded in the user-uploaded images or text.
- Capability inventory: The skill includes local file-writing capabilities through the
GIFBuilder.savemethod incore/gif_builder.py. No network operations or subprocess executions were found. - Sanitization: The skill does not perform sanitization or validation on user-provided text or image content before rendering them into the output GIF.
Audit Metadata