The Agent Skills Directory

Indirect Prompt Injection Surface: The skill processes potentially untrusted content from modernization prompts and project assessment reports to generate infrastructure plans and migration tasks. This surface could allow embedded logic in the reports to influence generated tasks or configurations. Ingestion points: Project assessment reports and custom modernization prompts provided via user input (SKILL.md). Boundary markers: The instructions do not define protective delimiters or specific instructions for the agent to ignore hidden directives within the input data. Capability inventory: The skill allows the agent to write files (plan.md, tasks.json) to the local directory and invoke external validation skills. Sanitization: No filtering or escaping mechanisms are specified for content extracted from reports before it is written to output files.

create-modernization-plan