The Agent Skills Directory

[SAFE]: The skill instructions and workflow focus on design strategy and recoloring existing logos. It does not attempt to access sensitive files, execute arbitrary code, or communicate with unauthorized external domains.
[PROMPT_INJECTION]: The skill processes untrusted user input to construct image generation prompts, creating an indirect prompt injection surface (Category 8). \n
Ingestion points: The skill ingests user data through the source_logo_description, brand_name, and brand_context fields in input-schema.json. \n
Boundary markers: No explicit delimiters or boundary markers are used to separate user-provided content from the agent's internal instructions. \n
Capability inventory: The skill utilizes the imagegen tool, as described in SKILL.md and prompt.md, to generate images based on the interpolated prompts. \n
Sanitization: There is no evidence of input filtering, sanitization, or validation performed on user-provided descriptions before they are used in prompt generation.

logo-colorway-generator