review-security-k8s-agents-main git:20260521.0dd191fA

Immutable. This exact content is served forever at /api/v1/blob/25ba8c0f67560a59.

---
name: review-security-k8s-agents-main
description: Orchestrates comprehensive Kubernetes security audits specifically tailored for AI agent workloads.
---
# Task
Coordinate AI agent security review sub-agents, gather findings, and produce a summarized JSON report.

# Workflow
## 1. Context Ingestion
Pass project context (from `review-security-k8s-understand`) to sub-agents.

## 2. Parallel Reviews
Launch in parallel:
- `review-security-k8s-agents-sandbox`
- `review-security-k8s-agents-firewall`
- `review-security-k8s-agents-credentials`
- `review-security-k8s-agents-prompt-injection`
- `review-security-k8s-agents-data-exfil`
- `review-security-k8s-agents-audit-logs`

**CRITICAL**: Instruct each to output JSON:
```json
[{"agent": "<skill-name>", "findings": [{"message": "<desc>", "file": "<name>", "line": "<num>"}]}]
```
(Return empty list if no findings). Wait for completion.

## 3. Triage & Filtering
Evaluate the raw findings against the project context to determine actual risk. Filter out findings that are functionally required by the workload's specific role or adequately mitigated by broader architectural controls. 
- *Example:* Filter out `hostPath` or `privileged` warnings for recognized infrastructure daemonsets (e.g., CSI drivers).
- *Example:* Downgrade or filter missing `NetworkPolicy` warnings if the context confirms a strict Service Mesh is handling all routing and authorization.

## 4. Aggregation
Merge the filtered findings into a single JSON array. Output MUST be valid JSON string (markdown blocks okay). Omit agents with no findings or return empty `findings`.