The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from business and technical requirements files, creating an attack surface where malicious content in those files could influence the agent's behavior.
Ingestion points: Requirements are loaded from business-requirements.yaml and technical-requirements.yaml located in the {base_directory}/requirements/ path as defined in SKILL.md.
Boundary markers: The instructions do not define strict delimiters (e.g., XML tags or specific markdown blocks) to separate requirements content from the system instructions, nor do they explicitly command the agent to ignore instructions embedded within the requirements.
Capability inventory: Across SKILL.md and the reference specifications, the skill is empowered to generate files and instructions for shell commands including npm, pnpm, and git, as well as file modifications and creations.
Sanitization: There are no documented procedures for sanitizing or validating the contents of the requirement files before they are parsed and used to generate implementation tasks.

implementation-planner