The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses bun to execute local scripts for style selection, image generation, and image optimization. These scripts are located in sibling directories within the platform's plugin root, which is a standard pattern for modular agent skills.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests user-supplied data, such as team member names and background descriptions, which are then interpolated into prompts for the image generation engine. While this represents a potential attack surface for prompt injection, it is the primary intended function of the skill and occurs within a structured, user-approved process.
Ingestion points: User-provided team member names and background preferences in SKILL.md (Step 1).
Boundary markers: The skill does not use specific delimiters for user input, but instructions emphasize transferring likeness rather than complex descriptions.
Capability inventory: Command execution via bun and file system writes via the generation and optimization scripts.
Sanitization: The instructions do not specify explicit sanitization, relying on the agent's standard handling of user-provided strings during script argument construction.

team-group-photo