busirocket-core-conventions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions in
SKILL.mdand therules/directory focus exclusively on code style and architecture. There are no attempts to override system prompts or bypass safety filters. - Data Exposure & Exfiltration (SAFE): No commands or code examples attempt to access sensitive system files (~/.ssh, .env, etc.) or send data to external servers.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill explicitly instructs the agent in
rules/core-agent-defaults.mdandrules/core-anti-patterns-dependencies.mdto avoid adding new dependencies without approval and prefers native implementations over libraries for trivial tasks. - Security Best Practices (INFO): The skill actively promotes security by including rules for input validation in API route handlers (
rules/core-anti-patterns-app-router.md) and discouraging the use of fat route handlers that mix business logic with HTTP concerns.
Audit Metadata