New to Claude Skills? Learn how to install them →

prompt-security on GitHub

Picoclaw Traffic Guardian

Free

Monitor and inspect traffic for lightweight AI gateways.

Get this skill

Free · Opens the source repo

What Picoclaw Traffic Guardian does

Picoclaw Traffic Guardian provides a foundational skill for monitoring network traffic in lightweight AI gateway proxies. This skill is designed for developers and security professionals looking to implement traffic inspection and detection capabilities without the overhead of a full proxy implementation. It focuses on egress detection, inbound injection detection, and posture integration, making it a valuable tool for maintaining the security posture of AI-driven applications.

The skill does not include a runtime proxy or implementation, allowing builders to customize their own solutions while adhering to the specifications outlined in the provided documentation. It emphasizes safety and privacy, ensuring that sensitive data is redacted before logging and that no automatic system changes are made. Users can expect to validate configurations and start monitoring traffic with a focus on lightweight operations, making it suitable for environments where performance is critical.

With an emphasis on opt-in monitoring, Picoclaw Traffic Guardian allows users to detect and log traffic patterns without imposing global changes to the system environment. It supports optional HTTPS inspection, contingent on user-provided trust configurations, which adds flexibility for various deployment scenarios. The skill's architecture is designed to facilitate integration with other Picoclaw components, such as the picoclaw-security-guardian, enabling a comprehensive security posture assessment while maintaining a modular approach to implementation.

This skill is ideal for developers and security engineers who need a customizable solution for traffic monitoring in AI applications. It provides the necessary building blocks for creating a secure and efficient traffic inspection system without the complexity of a full proxy setup.

When to use it

Use this skill when you need to implement traffic monitoring and inspection for AI gateways without a full proxy setup.

When not to use it

Avoid this skill if you require a complete proxy solution or automatic system changes for traffic management.

What you can build with it

Integrating with AI Gateway

Use Picoclaw Traffic Guardian to monitor traffic in AI gateways, ensuring compliance and security.

Custom Traffic Inspection

Build a tailored traffic inspection solution using the foundational capabilities provided by this skill.

Security Posture Assessment

Leverage the skill to gather insights for security posture assessments in AI-driven applications.

How to install Picoclaw Traffic Guardian

View source

1. Install with the skills CLI

npx skills add prompt-security/clawsec/picoclaw-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

Picoclaw 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 picoclaw-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="picoclaw-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 Picoclaw landing zone for runtime traffic monitoring:

  • lightweight AI gateway HTTP proxy inspection
  • optional HTTPS inspection with per-process CA trust
  • outbound exfiltration detection
  • inbound injection detection
  • redacted local threat logs
  • profile export for picoclaw-security-guardian

Do not add proxy runtime ownership to picoclaw-security-guardian or picoclaw-self-pen-testing. Those skills should profile, drift-check, or review this monitor's status, not run it.

Safety Contract

  • Opt-in only.
  • Detect-and-log by default.
  • No automatic system CA installation.
  • No global proxy environment changes.
  • No blocking in the first implementation.
  • Redact secrets before logs, summaries, or profile outputs.
  • Keep all state under PICOCLAW_TRAFFIC_GUARDIAN_HOME or $PICOCLAW_HOME/security/clawsec/traffic-guardian.

Builder Entry Points

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

PathIntended use
lib/Detector rules, redaction, profile export, report formatting
scripts/Start, stop, status, config validation, log query, profile export helpers
test/Unit tests, proxy fixture tests, redaction tests, profile integration tests

Required First Implementation Behavior

  1. Validate config without starting the proxy.
  2. Start monitor in foreground or explicit background mode.
  3. Scope proxy environment variables to the target Picoclaw gateway process.
  4. Inspect HTTP request/response text up to a bounded byte limit.
  5. Support optional HTTPS MITM only when the operator supplies per-process trust configuration.
  6. Emit JSONL findings with redacted snippets.
  7. Export a small profile fragment that picoclaw-security-guardian can include in deterministic posture profiles.

Out of Scope for v0.0.1 Implementation

  • automatic system trust-store mutation
  • transparent network interception
  • default blocking
  • sending traffic to external services
  • collecting full request/response bodies

Frequently asked questions about Picoclaw Traffic Guardian

Similar skills