New to Claude Skills? Learn how to install them →

prompt-security on GitHub

NanoClaw Traffic Guardian

Free

Baseline traffic monitoring for secure host-side proxy inspection.

Get this skill

Free · Opens the source repo

What NanoClaw Traffic Guardian does

NanoClaw Traffic Guardian is designed for developers and security engineers who need a reliable solution for monitoring network traffic in a containerized environment. This skill serves as a foundational specification for host-side proxy inspection, focusing on HTTP and optional HTTPS traffic. It provides the necessary tools to detect outbound exfiltration and inbound injection attempts while ensuring that sensitive information is redacted in logs. By establishing a secure monitoring baseline, it allows teams to maintain visibility into their network traffic without compromising security.

The skill emphasizes safety and privacy by adhering to a strict safety contract. It operates on an opt-in basis, ensuring that no automatic system changes are made, such as installing system CA certificates or accessing CA private keys from within containers. This makes it suitable for environments where security policies are stringent and where operators need to maintain control over their security configurations. The skill also includes features for logging and reporting findings in a structured JSONL format, making it easier to integrate with existing monitoring and alerting systems.

Developers can leverage the provided structure to implement their own detection rules, redaction methods, and reporting formats. The skill includes designated folders for various components, such as detector rules in the lib/ directory and IPC handlers in host-services/. This modular approach allows for easy customization and extension based on specific requirements. However, it is important to note that this skill does not include a proxy or runtime implementation out of the box, making it essential for users to familiarize themselves with the provided specifications and implementation guidelines before proceeding.

In summary, NanoClaw Traffic Guardian is ideal for those looking to enhance their security posture through effective traffic monitoring while maintaining strict control over their network environment. It is particularly useful as a companion to other NanoClaw tools, providing a robust framework for securing traffic without unnecessary complexity or risk.

When to use it

Use this skill when you need to implement traffic monitoring in a secure and controlled manner, particularly in environments with strict security policies.

When not to use it

This skill is not suitable for users looking for a fully packaged proxy solution or those who require immediate traffic interception capabilities.

What you can build with it

Secure Network Monitoring

Implement traffic monitoring in a containerized application to detect potential security threats.

Custom Detection Rules

Use the skill's modular structure to create and deploy custom detection rules tailored to specific security needs.

Integration with Existing Systems

Leverage the JSONL logging format to integrate findings with existing monitoring and alerting systems.

How to install NanoClaw Traffic Guardian

View source

1. Install with the skills CLI

npx skills add prompt-security/clawsec/nanoclaw-traffic-guardian --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by prompt-security

NanoClaw Traffic Guardian

This is a baseline specification skill. It intentionally does not ship a proxy or runtime implementation yet.

Vercel Skills Installation

Install with the Vercel Skills CLI for this harness:

npx skills add prompt-security/clawsec --skill nanoclaw-traffic-guardian -a openclaw -y

Release Artifact Verification

For standalone installs, verify the signed release manifest before trusting SKILL.md, skill.json, or the archive. The skill.json file is the package metadata/SBOM source, and the release pipeline signs checksums.json with the ClawSec release key.

set -euo pipefail

SKILL_NAME="nanoclaw-traffic-guardian"
VERSION="0.0.1-beta5"
REPO="prompt-security/clawsec"
TAG="${SKILL_NAME}-v${VERSION}"
BASE="https://github.com/${REPO}/releases/download/${TAG}"
ZIP_NAME="${SKILL_NAME}-v${VERSION}.zip"
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT

RELEASE_PUBKEY_SHA256="711424e4535f84093fefb024cd1ca4ec87439e53907b305b79a631d5befba9c8"

curl -fsSL "$BASE/checksums.json" -o "$TMP_DIR/checksums.json"
curl -fsSL "$BASE/checksums.sig" -o "$TMP_DIR/checksums.sig"
curl -fsSL "$BASE/signing-public.pem" -o "$TMP_DIR/signing-public.pem"
curl -fsSL "$BASE/$ZIP_NAME" -o "$TMP_DIR/$ZIP_NAME"
curl -fsSL "$BASE/SKILL.md" -o "$TMP_DIR/SKILL.md"
curl -fsSL "$BASE/skill.json" -o "$TMP_DIR/skill.json"

ACTUAL_PUBKEY_SHA256="$(openssl pkey -pubin -in "$TMP_DIR/signing-public.pem" -outform DER | shasum -a 256 | awk '{print $1}')"
if [ "$ACTUAL_PUBKEY_SHA256" != "$RELEASE_PUBKEY_SHA256" ]; then
  echo "ERROR: signing-public.pem fingerprint mismatch" >&2
  exit 1
fi

openssl base64 -d -A -in "$TMP_DIR/checksums.sig" -out "$TMP_DIR/checksums.sig.bin"
openssl pkeyutl -verify -rawin -pubin \
  -inkey "$TMP_DIR/signing-public.pem" \
  -sigfile "$TMP_DIR/checksums.sig.bin" \
  -in "$TMP_DIR/checksums.json" >/dev/null

hash_file() {
  if command -v shasum >/dev/null 2>&1; then
    shasum -a 256 "$1" | awk '{print $1}'
  else
    sha256sum "$1" | awk '{print $1}'
  fi
}

verify_manifest_file() {
  asset="$1"
  path="$2"
  expected="$(jq -r --arg asset "$asset" '.files[$asset].sha256 // empty' "$TMP_DIR/checksums.json")"
  if [ -z "$expected" ]; then
    echo "ERROR: checksums.json missing $asset" >&2
    exit 1
  fi
  actual="$(hash_file "$path")"
  if [ "$actual" != "$expected" ]; then
    echo "ERROR: checksum mismatch for $asset" >&2
    exit 1
  fi
}

expected_archive="$(jq -r '.archive.sha256 // empty' "$TMP_DIR/checksums.json")"
if [ -z "$expected_archive" ]; then
  echo "ERROR: checksums.json missing archive.sha256" >&2
  exit 1
fi
actual_archive="$(hash_file "$TMP_DIR/$ZIP_NAME")"
if [ "$actual_archive" != "$expected_archive" ]; then
  echo "ERROR: archive checksum mismatch" >&2
  exit 1
fi

verify_manifest_file "SKILL.md" "$TMP_DIR/SKILL.md"
verify_manifest_file "skill.json" "$TMP_DIR/skill.json"

echo "Signed release manifest, archive, SKILL.md, and skill.json verified."

Only install or extract the archive after this verification succeeds.

Scope

Builders should use this skill as the NanoClaw landing zone for runtime traffic monitoring:

  • host-side HTTP proxy inspection
  • optional HTTPS inspection with host-held CA material
  • outbound exfiltration detection
  • inbound injection detection
  • redacted local threat logs
  • MCP tools for status, findings, and config checks
  • IPC handlers for container-safe host communication

Prefer this as an optional companion to clawsec-nanoclaw, not as a mandatory extension of the existing advisory/signature/integrity suite.

Safety Contract

  • Opt-in only.
  • Detect-and-log by default.
  • No automatic system CA installation.
  • No CA private key access from the container.
  • No blocking in the first implementation.
  • Redact secrets before logs or MCP responses.
  • Keep all state under NANOCLAW_TRAFFIC_GUARDIAN_HOME or the host-managed NanoClaw security data directory.

Builder Entry Points

Read SPEC.md before implementing. Use the placeholder folders as follows:

PathIntended use
lib/Detector rules, redaction, types, report formatting
host-services/Host-side proxy lifecycle, log access, IPC handlers
mcp-tools/Container-side MCP tools for status and findings
test/Unit tests, host/container IPC tests, redaction tests

Required First Implementation Behavior

  1. Validate config without starting the proxy.
  2. Start monitor through a host-managed lifecycle path.
  3. Keep CA key material on the host side.
  4. Inspect HTTP request/response text up to a bounded byte limit.
  5. Support optional HTTPS MITM only when the operator supplies per-runtime trust configuration.
  6. Emit JSONL findings with redacted snippets.
  7. Expose MCP tools that return status and redacted findings only.

Out of Scope for v0.0.1 Implementation

  • automatic system trust-store mutation
  • transparent network interception
  • default blocking
  • sending traffic to external services
  • exposing raw request/response bodies to the container

Frequently asked questions about NanoClaw Traffic Guardian

Similar skills