prisma
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill establishes comprehensive naming and structural rules for Prisma models and relations to ensure code quality and consistency across projects.\n- [EXTERNAL_DOWNLOADS]: Recommends the use of the
@explita/prisma-audit-logNPM package for implementing audit trails, which is a legitimate architectural recommendation for the stated use case.\n- [COMMAND_EXECUTION]: Directs the user to runbun prisma generateto update the Prisma client after schema modifications, which is a standard and benign operational command in the Prisma workflow.\n- [INDIRECT_PROMPT_INJECTION]: Identifies the attack surface related to processing schema files.\n - Ingestion points: The skill is designed to process and guide the editing of
schema.prismafiles within the local project environment.\n - Boundary markers: Absent; the workflow assumes that the schema files are trusted assets managed by the developer.\n
- Capability inventory: Includes the ability to trigger Prisma client regeneration via
bun prisma generate(SKILL.md).\n - Sanitization: None; the skill relies on the agent applying structural rules to the schema content without specific sanitization of the input file content.
Audit Metadata