AGENT SKILL

pipelock

Secure agent HTTP requests through a scanning proxy that catches credential leaks, SSRF, and prompt injection

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
pipelock
homepage
https://github.com/luckyPipewrench/pipelock
metadata
{ "clawdbot": { "emoji": "🔒", "requires": { "os": [ "darwin", "linux" ], "bins": [ "pipelock" ] } } }
description
Secure agent HTTP requests through a scanning proxy that catches credential leaks, SSRF, and prompt injection
user-invocable
true

03 SKILL.md 正文

Pipelock Security Harness

Pipelock is a fetch proxy that sits between you and the internet. Every outbound HTTP request passes through a 7-layer scanner pipeline that catches API key leaks, SSRF attempts, prompt injection, and data exfiltration.

Installation

# Homebrew (macOS/Linux)
brew install luckyPipewrench/tap/pipelock

# Or Go
go install github.com/luckyPipewrench/pipelock/cmd/pipelock@latest

Quick Start

Generate a config and start the proxy:

pipelock generate config --preset balanced -o pipelock.yaml
pipelock run --config pipelock.yaml

The proxy listens on http://localhost:8888. Route your HTTP requests through it:

curl "http://localhost:8888/fetch?url=https://example.com/api/data"

Using with MCP Servers

Wrap any MCP server to scan its responses for prompt injection:

pipelock mcp proxy -- npx @modelcontextprotocol/server-filesystem /path/to/dir

What It Catches

  1. SSRF - blocks requests to internal IPs, catches DNS rebinding
  2. Domain blocklist - blocks exfiltration targets (pastebin, transfer.sh)
  3. Rate limiting - detects unusual request bursts
  4. DLP patterns - detects API keys (Anthropic, OpenAI, AWS, GitHub) in URLs and bodies
  5. Env var leaks - detects your actual env var values in outbound traffic
  6. Entropy analysis - flags high-entropy strings that look like secrets
  7. URL length limits - flags unusually long URLs suggesting exfiltration

Actions

Configure what happens when a threat is detected:

  • block - reject the request
  • strip - redact the match and forward
  • warn - log and pass through
  • ask - terminal prompt for human approval (y/N/s)

Presets

  • balanced - default, good for most setups
  • strict - blocks aggressively, tight thresholds
  • audit - detect and log only, never blocks
  • claude-code - tuned for Claude Code agent workflows
  • cursor - tuned for Cursor IDE
  • generic-agent - works with any agent framework

Workspace Integrity

Detect unauthorized changes to your workspace files:

pipelock integrity init ./workspace
pipelock integrity check ./workspace

More Info

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0