The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user requests for database modeling and data filtering (e.g., "建模", "建表") to generate structured DSL YAML and CEL (Common Expression Language) expressions. There is a potential risk where malicious user input could be injected into these generated structures if the agent does not perform adequate sanitization.
Ingestion points: User-supplied requirements for application schemas, entity definitions, and data filtering criteria as described in SKILL.md and references/EntityDataFilterUsage.md.
Boundary markers: Absent. The instructions do not specify delimiters or "ignore embedded instructions" warnings for the generated DSL content.
Capability inventory: The skill facilitates the generation of YAML files and API payloads intended for use with the makecli tool and the Make platform's Data and Meta APIs; it does not directly execute scripts or commands itself.
Sanitization: Absent. There are no instructions for the agent to escape, validate, or filter user-provided strings before they are placed into the filter.expression or YAML property fields.

makedsl