carousel-styles
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's instructions or Python reference code.
- [DYNAMIC_EXECUTION]: The skill provides Python code for image manipulation using the Pillow library. These functions are standard utilities for resizing, rotating, and layering images and do not use unsafe execution methods or process untrusted inputs in a dangerous way.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data. Ingestion points: User-provided design references and carousel topic requests (SKILL.md). Boundary markers: None explicitly defined in the provided logic. Capability inventory: Image processing (PIL) and text generation (LLM) (reference.md). Sanitization: The pipeline logic includes length caps, word verification, and deduplication (SKILL.md).
Audit Metadata