The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted text from PRDs and functional specifications to generate output without sanitization or boundary markers.
Ingestion points: Documentation files including SPEC and PRD files are read from the project directory as specified in the 'Input analysis' section of SKILL.md.
Boundary markers: The instructions do not provide delimiters or negative constraints to ensure the agent ignores instructional content potentially hidden within the source documents.
Capability inventory: The skill performs file system read operations on project documentation and write operations to create Mermaid (.mmd) files and update the AGENTS.md file.
Sanitization: No validation or escaping logic is defined for the content extracted from external specifications before it is used for modeling.

workflow-erd