type-safety-validation
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill creates an indirect prompt injection surface by establishing workflows where an agent ingests untrusted data and uses it to drive side effects in a database. 1. Ingestion points: Untrusted results and API responses processed in SKILL.md and references/ty-type-checker-patterns.md. 2. Boundary markers: The skill instructs the use of Zod schemas and explicit type narrowing as boundaries. 3. Capability inventory: Code examples include database write operations such as db.user.create and Prisma-based mutations. 4. Sanitization: The skill provides extensive sanitization patterns including Zod validation (.parse()), isinstance() checks, and type guards, which mitigate but do not eliminate the risk of the injection surface.
Recommendations
- AI detected serious security threats
Audit Metadata