gpt-taste
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user prompt data to determine its output structure, representing a standard injection surface for code-generation utilities.
- Ingestion points: The skill uses the character count of the user prompt to seed its internal randomization logic in SKILL.md.
- Boundary markers: There are no specific delimiters or instructional wrappers defined to isolate user-provided content from the skill's core instructions.
- Capability inventory: The skill is capable of generating complex React components, Tailwind CSS layouts, and GSAP animation sequences.
- Sanitization: No explicit sanitization or filtering logic is provided for the incoming prompt data before it influences the generated output.
- [EXTERNAL_DOWNLOADS]: The skill utilizes external assets and third-party libraries to fulfill its design requirements.
- References the use of
picsum.photosfor high-resolution placeholder imagery, which is a well-known and standard industry service. - Instructs the integration of established and reputable packages such as
@gsap/reactand@phosphor-icons/reactfor UI functionality.
Audit Metadata