flux-migrate
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface via ingestion of untrusted project files.
- Ingestion points: The skill reads local project files including Prisma schemas, ORM configs (Alembic, Drizzle, Knex), and migration directories to determine database state and tooling.
- Boundary markers: The instructions lack specific delimiters or system-level directives to ignore instructions that might be embedded within comments or metadata of the files being read.
- Capability inventory: The agent has access to powerful tools such as
Bash,Write,Edit, andTaskwhich could be manipulated if the agent follows malicious instructions found in project files. - Sanitization: There is no defined process for validating or sanitizing the content of the schema files before they are processed by the skill's logic.
Audit Metadata