The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input describing creative requests (e.g., 'assets for my product launch') to determine the production plan and tool sequences.
Ingestion points: User-provided definitions for 'Outcome', 'What exists', and 'Deliverables' are processed by the agent (defined in SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user input.
Capability inventory: The skill utilizes command execution via docs/creative_cli.py, package installation via pip, and network API calls to FAL.ai.
Sanitization: No explicit sanitization or validation logic for the user-provided request strings is mentioned in the instructions.
[COMMAND_EXECUTION]: The skill instructs the agent to perform local environment setup and execution of project-specific scripts.
Evidence: The skill commands the use of pip install requests and python docs/creative_cli.py test to verify the environment and automate asset generation.

orchestrator