organization-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Provides instructions to run
npx @better-auth/cli migratefor database schema updates. - [EXTERNAL_DOWNLOADS]: Utilizes
npxto retrieve and execute the@better-auth/clipackage from the npm registry. - [INDIRECT_PROMPT_INJECTION]: The skill outlines patterns for handling user-controlled data such as organization names, slugs, and roles that are later used in system operations and emails.
- Ingestion points: User-provided organization names, slugs, logo URLs, and metadata in SKILL.md.
- Boundary markers: The example snippets do not use specific delimiters or instructions to prevent the agent from obeying embedded instructions in user data.
- Capability inventory: The skill utilizes APIs for database modification and provides examples for sending emails via a
sendEmailutility. - Sanitization: No explicit data sanitization or escaping mechanisms are demonstrated in the provided code examples.
Audit Metadata