The Agent Skills Directory

[PROMPT_INJECTION]: Indirect prompt injection surface detected where user-provided data is used to drive agent output.
Ingestion points: User descriptions of entities, data models, and requirements in SKILL.md.
Boundary markers: Absent; the instructions do not specify delimiters or constraints to prevent the agent from following instructions embedded within the user data description.
Capability inventory: The skill uses Read, Write, and Edit tools, which allow the agent to modify the file system based on potentially untrusted input.
Sanitization: Absent; no explicit validation or sanitization of input data is defined before the agent generates code or migration scripts.

design-schema