# Model Safety

> Review AI features for misuse, prompt injection, unsafe tool use, data exposure, unreliable outputs, oversight, and operational controls.

- Skill: `egeetas/model-safety` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add egeetas/model-safety`
- Raw SKILL.md: https://api.skillmd.com/api/skills/egeetas/model-safety/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: egeetas (https://skillmd.com/u/egeetas)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/egeetas/model-safety

---


# Model Safety

Apply to AI features that process untrusted content, retrieve private data, call tools, make consequential recommendations, or act on external systems.

## Review Areas

- Threat actors, misuse cases, prohibited outcomes, affected users, and consequence severity.
- Prompt injection and instruction/data separation across uploads, web content, retrieval, connectors, and tool outputs.
- Least-privilege tools, allowlists, argument validation, sandboxing, rate limits, approvals, and reversible actions.
- Data minimization, tenant isolation, retention, logging, redaction, model-provider boundaries, and secret handling.
- Hallucination, uncertainty, citations, abstention, validation, human review, and appeal or recovery paths.
- Adversarial evaluations, monitoring, incident response, and staged rollout.

Do not represent prompt wording alone as a security boundary. Recommend layered technical controls and state residual risk.