prisma-cli-migrate-diff

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and process external data sources such as database schema files and migration directories. These sources could potentially contain malicious instructions intended to influence the agent's behavior during the diffing process.
  • Ingestion points: The skill reads data from ./prisma/schema.prisma, ./prisma/migrations directories, and external databases via --from-url or --to-url parameters.
  • Boundary markers: There are no explicit instructions or markers defined to help the agent distinguish between tool output/data and executable instructions.
  • Capability inventory: The skill utilizes shell command execution via the prisma CLI and file system write operations through shell redirection (e.g., > prisma/migrations/0_init/migration.sql).
  • Sanitization: No sanitization or validation of the schema content or database output is specified before processing.
  • [DYNAMIC_EXECUTION]: The skill demonstrates the dynamic generation of SQL scripts based on the comparison of two schema states. These scripts are intended to be executed against a database or saved to the local filesystem for future execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:05 AM
Security Audit — agent-trust-hub — prisma-cli-migrate-diff