# Risk Assessment

> MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, and when assessing environment risk level. SHOULD be invoked manually before any new environment interaction.

- Skill: `griddynamics/risk-assessment-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add griddynamics/risk-assessment-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/griddynamics/risk-assessment-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- License: Apache-2.0
- Author: griddynamics (https://skillmd.com/u/griddynamics)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/griddynamics/risk-assessment-2

---


<risk_assessment>

<process>

1. Assess access to dangerous MCPs (database, cloud, S3, similar).
2. Assign risk level: low, medium, high, critical.
3. Read-only or local = low.
4. Shared dev/stage/qa = medium.
5. +1 level for write access.
6. +1 level for access to higher environments including production.
7. Output `AI Risk Assessment: {LEVEL}`.

Escalation:

8. MEDIUM: warn user, explain failure modes.
9. HIGH: require user to understand data loss risk.
10. CRITICAL: block execution, require external risk reduction. OVERRIDE NOT ALLOWED.

</process>

<pitfalls>

- Defaulting to "low" without checking accessible MCPs.
- Not re-assessing when new environments join mid-session.

</pitfalls>

</risk_assessment>