| name | llmops-security-reviewer |
| description | Review GenAI workloads for prompt injection, tool permissions, data exfiltration, RAG sources, sensitive prompt logging, evals, guardrails, and model access. |
| version | 1.0.0 |
| since | 2026-07-28 |
| last_modified | 2026-07-28 |
| authors | ["platform-engineering"] |
| stability | stable |
| min_platform_version | {"codex":"unknown","amazon-q":"unknown","antigravity":"unknown","auggie":"unknown","bob":"unknown","claude-code":"unknown","cline":"unknown","codebuddy":"unknown","continue":"unknown","costrict":"unknown","crush":"unknown","github-copilot":"unknown","gitlab-duo":"unknown","factory":"unknown","forgecode":"unknown","opencode":"unknown","openhands":"unknown","cursor":"unknown","roo-code":"unknown","kiro":"unknown","junie":"unknown","gemini-cli":"unknown","iflow":"unknown","kilocode":"unknown","kimi":"unknown","lingma":"unknown","pi":"unknown","qoder":"unknown","qwen":"unknown","windsurf":"unknown","ollama":"unknown"} |
| deprecated_since | null |
| replaces | null |
| supersedes | [] |
| changelog | [{"version":"1.0.0","date":"2026-07-28","change":"Initial generated production-ready SDLC / DevSecOps skill"}] |
Llmops Security Reviewer
Purpose
Review GenAI workloads for prompt injection, tool permissions, data exfiltration, RAG sources, sensitive prompt logging, eval sets, guardrails, and model access. Treat regulatory, security, and operational references as review and evidence guidance, not legal advice.
When to use
- LLMOps security decisions, controls, or operating practices need independent review.
- A change affects LLMOps security artifacts such as prompt template, tool permission, RAG source, prompt log, eval set, guardrail policy.
- The user needs evidence-oriented findings for risks such as prompt injection, tool abuse, data exfiltration, untrusted RAG content, sensitive prompt logging, uncontrolled model access.
- Audit, security, operations, or platform stakeholders need a concise readiness position.
- Existing documentation, tickets, tests, or logs must be turned into actionable remediation items.
Operating model
- Identify the relevant LLMOps security artifacts, owners, systems, environments, and review boundary.
- Compare the available artifacts against expected signals such as red-team eval, retrieval allowlist, tool audit, DLP finding, guardrail result, access policy.
- Separate confirmed gaps from assumptions, missing evidence, and advisory improvement opportunities.
- Rate findings by operational, security, compliance, customer, and auditability impact.
- Recommend minimal remediation steps, validation evidence, owners, and review cadence.
Spec-Driven Change Context
- Treat repository specs, ADRs, runbooks, change proposals, design notes, and task files as durable context that outlives a chat session.
- For non-trivial changes, prefer a checked-in change artifact or equivalent proposal/design/tasks record before implementation begins.
- Capture requirement deltas explicitly: added, modified, removed, deprecated, or unchanged behavior.
- Keep implementation tasks traceable to acceptance criteria, affected specs, validation commands, and owners.
- During verification, compare the implementation against the proposal, design decisions, task checklist, and spec deltas.
- After completion, sync or archive completed change artifacts so the repository's source of truth reflects the final behavior.
- If the repository has no spec workflow yet, report the missing artifact and provide a minimal proposal/spec/tasks outline instead of relying on chat-only intent.
Skill-Specific Review Scope
- Primary artifacts: prompt template, tool permission, RAG source, prompt log, eval set, guardrail policy.
- Risk themes: prompt injection, tool abuse, data exfiltration, untrusted RAG content, sensitive prompt logging, uncontrolled model access.
