ln-723-seed-data-generator
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is configured to fetch missing reference files from the author's GitHub repository (
https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/) usingWebFetchif theshared/directory is missing locally. This is a self-bootstrapping mechanism for the skill's own documentation. - [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it parses untrusted local data (ORM schema files) to guide its generation logic.
- Ingestion points: ORM schema files (Drizzle, Prisma, TypeORM, EF Core, SQLAlchemy, Django ORM).
- Boundary markers: None specified in the instructions for delimiting input data.
- Capability inventory: File system read (schemas), file system write (seed files), and network access via
WebFetch(reference files). - Sanitization: No explicit sanitization or validation of the input schema content is defined beyond structure parsing.
Audit Metadata