Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/generating-orm-code/Gen Agent Trust Hub

generating-orm-code

Warn

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: MEDIUMPRIVILEGE_ESCALATIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PRIVILEGE_ESCALATION]: The scripts scripts/generate_model.py and scripts/generate_schema.py contain a generate_script method that applies chmod(0o755) to dynamically created files, granting them execution permissions.
  • [DYNAMIC_EXECUTION]: The skill is designed to generate executable code and scripts based on user-provided or database-derived content, which is then written to the filesystem.
  • [COMMAND_EXECUTION]: The instructions in SKILL.md direct the agent to execute shell commands such as npx prisma migrate, typeorm migration:generate, and alembic revision, requiring the Bash tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from database schemas (information_schema, pg_catalog) and has the capability to write files and execute shell commands. Maliciously crafted database metadata could potentially influence agent behavior during the generation process.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and resources from well-known and trusted services including Prisma, TypeORM, SQLAlchemy, Drizzle ORM, and Django. These are assessed as SAFE and do not contribute to verdict escalation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 9, 2026, 03:42 AM