The Agent Skills Directory

Indirect Prompt Injection (HIGH): The skill's architecture creates a high-risk surface by processing untrusted external data while possessing file modification permissions.
Ingestion points: The scripts/schema_validator.py script identifies and reads user project files using pathlib.Path.glob (Line 38) and read_text (Line 55).
Boundary markers: There are no boundary markers, delimiters, or explicit instructions to ignore embedded commands within the processed schema files.
Capability inventory: According to SKILL.md, the skill is granted Read, Write, Edit, Glob, and Grep permissions.
Sanitization: No sanitization, escaping, or schema validation of external content is performed; the script uses raw regular expression matching on the untrusted file content.

database-design