The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to take brainstorming or design inputs and transform them into implementation plans containing Python code and shell commands (such as pytest and git commit). There is a risk that malicious instructions present in the input data could be incorporated into the generated plan, leading to the execution of unintended code or commands when the plan is followed.
Ingestion points: Brainstorming or design context provided to the agent before planning.
Boundary markers: The skill does not utilize specific boundary markers or instructions to the agent to disregard potentially malicious content within the input data.
Capability inventory: The skill generates implementation steps including file creation, shell command execution (pytest), and version control operations (git add/commit).
Sanitization: No explicit sanitization or validation of the input brainstorming data is performed before it is used to generate the plan components.

Writing Plans