aks-network-capture
1 finding (1 critical), mainly command injection. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Collects bounded packet captures from AKS nodes and Azure network configuration for wire-level evidence. WHEN: \"capture packets on an AKS node\", \"take a pcap\", \"run tcpdump on AKS\", \"prove where packets drop\". Use for explicit packet-capture intent after read-only diagnostics, not general AKS connectivity or ingress troubleshooting.
- Package
- 13 files, 77 KB
- SKILL.md
- 325 words, 7 sections
- Code
- Shell (6), PowerShell (5)
- License
- MIT
SKILL.md covers: AKS Network Capture · Quick Reference · When to Use This Skill · MCP Tools · Host Capability Gate · Workflow/Steps · Error Handling
Findings
CRITICAL Remote fetch followed by execution Command Injectionpipeline
Content is downloaded from the network and subsequently executed. This is a classic remote code execution attack pattern.
scripts/generate-test-traffic.sh:149
#!/usr/bin/env bash
# Generate bounded test traffic from a pod network namespace.
# Exit codes: 0 = success/help, 1 = execution failure, 2 = usage/argument error.
set -euo pipefail
DEBUG_IMAGE="mcr.microsoft.com/cbl-mariner/busybox:2.0@sha256:e4fb4d51fc9b70d6cdc1ce66a0af02ab40554d2ca632e1d188fabc76What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 2.9 KB |
references/capture-authorization.md | doc | 1.4 KB |
scripts/collect-azure-network-info.ps1 | script | 7.9 KB |
scripts/collect-azure-network-info.sh | script | 7.0 KB |
scripts/create-capture.ps1 | script | 12 KB |
scripts/create-capture.sh | script | 12 KB |
scripts/generate-test-traffic.ps1 | script | 5.4 KB |
scripts/generate-test-traffic.sh | script | 6.1 KB |
scripts/retrieve-captures.ps1 | script | 9.4 KB |
scripts/retrieve-captures.sh | script | 8.1 KB |
scripts/run-capture.sh | script | 2.4 KB |
scripts/setup-capture-configmap.ps1 | script | 1.7 KB |
scripts/setup-capture-configmap.sh | script | 1.2 KB |
External hosts referenced
kubernetes.io learn.microsoft.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
RUN_ID TARGET_PORT RETRIEVE_RUN_ID VNET_SUBNET_ID CAPTURE_OUTPUT_DIR OUT_DIR WORKSPACE_DIR CAPTURE_ID CONFIGMAP_NAME OUTPUT_DIR OUTPUT_PATH PCAP_PATH AZURE_HTTP_USER_AGENT BUNDLE_PATH CAPTURE_MOUNT_PATH CAPTURE_OUTPUT_PATH RUN_DIR RUN_TOKEN CAPTURES_DIR
Package contents recorded 2026-10-22 at commit f49ac319a7d3. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/microsoft/azure-skills
- Raw scan result: microsoft-azure-skills-github-plugins-aks-skills-skills-aks-network-capture-scan.json
- Badge for your README:
- Request a re-scan