{"id":"9a43b276-9bef-4889-a014-b251de28e650","shortId":"XtSGVF","kind":"skill","title":"Block agent egress, MCP prompt injection, and secret exfiltration before agents touch the open internet with Pipelock","tagline":"Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.","description":"# Block agent egress, MCP prompt injection, and secret exfiltration before agents touch the open internet with Pipelock\n\nPut an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.\n\n## Prerequisites\n\nHomebrew or Go, terminal, supported agent runtime or IDE integration\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- brew install luckyPipewrench/tap/pipelock\n- docker pull ghcr.io/luckypipewrench/pipelock:latest\n- go install github.com/luckyPipewrench/pipelock/cmd/pipelock@latest\n- docker run -p 8888:8888 -v ./pipelock.yaml:/config/pipelock.yaml:ro \\\n\nRequirements and caveats from upstream:\n- pipelock check --url \"https://docs.python.org/3/\" # allowed\n- # Docker\n- # From source (requires Go 1.25+)\n\nBasic usage or getting-started notes:\n- [Quick Start](#quick-start) · [What It Does](#what-it-does) · [Docs](docs/) · [Blog](https://pipelab.org/blog/) · [Ask Dosu](https://app.dosu.dev/bcccd1cf-be85-4c0e-ae05-edeb0ff50b59/ask)\n- bash\n- # Set up (discovers IDE configs, generates config, verifies detection)\n\n- Source: https://github.com/luckyPipewrench/pipelock\n- Extracted from upstream docs: https://raw.githubusercontent.com/luckyPipewrench/pipelock/HEAD/README.md\n\n## Documentation\n\n- https://pipelab.org\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock/)","tags":["block","agent","egress","mcp","prompt","injection","and","secret","exfiltration","before","agents","touch"],"capabilities":["skill","source-agentskillexchange","skill-block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,543 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:09:37.823Z","embedding":null,"createdAt":"2026-05-18T13:15:25.486Z","updatedAt":"2026-05-18T19:09:37.823Z","lastSeenAt":"2026-05-18T19:09:37.823Z","tsv":"'/3/':142 '/bcccd1cf-be85-4c0e-ae05-edeb0ff50b59/ask)':179 '/blog/)':174 '/config/pipelock.yaml':130 '/luckypipewrench/pipelock':193 '/luckypipewrench/pipelock/cmd/pipelock@latest':122 '/luckypipewrench/pipelock/head/readme.md':200 '/luckypipewrench/pipelock:latest':117 '/pipelock.yaml':129 '/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock/)':209 '1.25':149 '8888':126,127 'agent':2,11,28,40,45,54,71,83,93,204 'agentskillexchange.com':208 'agentskillexchange.com/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock/)':207 'allow':143 'app.dosu.dev':178 'app.dosu.dev/bcccd1cf-be85-4c0e-ae05-edeb0ff50b59/ask)':177 'ask':175 'bash':180 'basic':150 'block':1,44 'blog':171 'brew':110 'call':32,75 'caveat':134 'check':138 'config':185,187 'contain':23,66 'detect':189 'discov':183 'doc':169,170,197 'docker':113,123,144 'docs.python.org':141 'docs.python.org/3/':140 'document':201 'dosu':176 'egress':3,46 'environ':109 'exchang':206 'exfiltr':9,52 'extract':194 'firewal':21,64 'front':26,69 'generat':186 'get':154 'getting-start':153 'ghcr.io':116 'ghcr.io/luckypipewrench/pipelock:latest':115 'github.com':121,192 'github.com/luckypipewrench/pipelock':191 'github.com/luckypipewrench/pipelock/cmd/pipelock@latest':120 'go':90,118,148 'homebrew':88 'ide':96,184 'inject':6,49 'inlin':20,63 'instal':98,102,111,119 'integr':97 'internet':15,58 'layer':24,67 'local':42,85 'luckypipewrench/tap/pipelock':112 'match':107 'mcp':4,34,47,77 'network':29,72 'note':156 'open':14,57 'p':125 'path':105 'pipelab.org':173,202 'pipelab.org/blog/)':172 'pipelock':17,60,137 'prerequisit':87 'prompt':5,48 'pull':114 'put':18,61 'quick':157,160 'quick-start':159 'raw.githubusercontent.com':199 'raw.githubusercontent.com/luckypipewrench/pipelock/head/readme.md':198 'requir':132,147 'ro':131 'run':124 'runtim':94 'secret':8,43,51,86 'set':181 'setup':104 'skill':205 'skill-block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock' 'sourc':146,190,203 'source-agentskillexchange' 'start':155,158,161 'support':92 'termin':91 'tool':31,74 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'touch':12,55 'traffic':30,35,73,78 'trust':38,81 'upstream':101,136,196 'url':139 'usag':151 'use':99 'v':128 'verifi':188 'what-it-do':165","prices":[{"id":"c9aea921-6423-46a3-a2a0-327a6ad29bfe","listingId":"9a43b276-9bef-4889-a014-b251de28e650","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:15:25.486Z"}],"sources":[{"listingId":"9a43b276-9bef-4889-a014-b251de28e650","source":"github","sourceId":"agentskillexchange/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock","isPrimary":false,"firstSeenAt":"2026-05-18T13:15:25.486Z","lastSeenAt":"2026-05-18T19:09:37.823Z"}],"details":{"listingId":"9a43b276-9bef-4889-a014-b251de28e650","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"f11215ddbb8fa671b9c9c015f22e7b041a1dd819","skill_md_path":"skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Block agent egress, MCP prompt injection, and secret exfiltration before agents touch the open internet with Pipelock","description":"Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/block-agent-egress-mcp-prompt-injection-and-secret-exfiltration-before-agents-touch-the-open-internet-with-pipelock"},"updatedAt":"2026-05-18T19:09:37.823Z"}}