slack-gif-creator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it ingests untrusted user descriptions to generate animation frames.
- Ingestion points: User-provided descriptions in the prompt context (e.g., 'make me a GIF of X doing Y') located in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or warnings to isolate user descriptions from the animation logic.
- Capability inventory: The skill can perform file writes to the local filesystem using the
savemethod incore/gif_builder.py. - Sanitization: No specific input sanitization or validation of the generated content is implemented within the provided toolkit.
- [SAFE]: The skill's codebase consists of modular Python scripts focused on image processing and mathematical animation logic. It utilizes well-known, legitimate libraries (Pillow, NumPy, ImageIO) for its operations. There are no instances of hardcoded credentials, unauthorized network communication, or attempts to gain elevated privileges.
Audit Metadata