{"id":"458bff4f-d077-4206-926f-cecc1bf1d8f4","shortId":"u3TZYQ","kind":"skill","title":"Block unsafe agent actions and scan newly added skills with AgentGuard","tagline":"Add a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.","description":"# Block unsafe agent actions and scan newly added skills with AgentGuard\n\nAdd a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.\n\n## Prerequisites\n\nNode.js, supported agent runtime such as Claude Code or OpenClaw, local skill directories and agent action hooks\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- npm install -g @goplus/agentguard\n- git clone https://github.com/GoPlusSecurity/agentguard.git\n- npm install @goplus/agentguard\n\nRequirements and caveats from upstream:\n- # Requires the local OpenClaw Gateway at 127.0.0.1:18789.\n- | 3 | **Network Exposure** | Detects dangerous ports bound to 0.0.0.0 (Redis, Docker API, MySQL, etc.), checks firewall status, flags suspicious outbound connections |\n- **Note:** Patrol requires an OpenClaw environment. For non-OpenClaw setups, use /agentguard scan and /agentguard report for manual security checks.\n\nBasic usage or getting-started notes:\n- 8 comprehensive security checks run on a configurable schedule\n- # skills, and reports matches back. Run in cron / on boot.\n- # Optional: after one subscribe run, install an OpenClaw isolated cron job that\n\n- Source: https://github.com/GoPlusSecurity/agentguard\n- Extracted from upstream docs: https://raw.githubusercontent.com/GoPlusSecurity/agentguard/HEAD/README.md\n\n## Documentation\n\n- https://github.com/GoPlusSecurity/agentguard\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard/)","tags":["block","unsafe","agent","actions","and","scan","newly","added","skills","with","agentguard","agentskillexchange"],"capabilities":["skill","source-agentskillexchange","skill-block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard","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-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard","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 (1,603 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":"2026-05-18T19:09:38.136Z","embedding":null,"createdAt":"2026-05-18T13:15:26.086Z","updatedAt":"2026-05-18T19:09:38.136Z","lastSeenAt":"2026-05-18T19:09:38.136Z","tsv":"'/agentguard':153,156 '/goplussecurity/agentguard':203,214 '/goplussecurity/agentguard.git':103 '/goplussecurity/agentguard/head/readme.md':210 '/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard/)':221 '0.0.0.0':128 '127.0.0.1':118 '18789':119 '3':120 '8':169 'action':4,19,36,51,81 'ad':8,40 'add':12,44 'agent':3,18,35,50,68,80,216 'agentguard':11,43 'agentskillexchange.com':220 'agentskillexchange.com/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard/)':219 'api':131 'audit':27,59 'back':182 'basic':162 'block':1,20,33,52 'boot':187 'bound':126 'caveat':109 'check':134,161,172 'claud':72 'clone':100 'code':73 'command':22,54 'comprehens':170 'configur':176 'connect':140 'cron':185,197 'danger':21,53,124 'detect':123 'directori':78 'doc':207 'docker':130 'document':211 'environ':94,146 'etc':133 'evalu':17,49 'exchang':218 'exposur':25,57,122 'extract':204 'firewal':135 'flag':137 'g':97 'gateway':116 'get':166 'getting-start':165 'git':99 'github.com':102,202,213 'github.com/goplussecurity/agentguard':201,212 'github.com/goplussecurity/agentguard.git':101 'goplus/agentguard':98,106 'guard':15,47 'hook':82 'instal':83,87,96,105,193 'isol':196 'job':198 'local':76,114 'manual':159 'match':92,181 'mysql':132 'network':121 'new':28,60 'newli':7,39 'node.js':66 'non':149 'non-openclaw':148 'note':141,168 'npm':95,104 'one':190 'openclaw':75,115,145,150,195 'option':188 'outbound':139 'path':90 'patrol':142 'port':125 'prerequisit':65 'raw.githubusercontent.com':209 'raw.githubusercontent.com/goplussecurity/agentguard/head/readme.md':208 'redi':129 'report':157,180 'requir':107,112,143 'run':32,64,173,183,192 'runtim':14,46,69 'scan':6,38,154 'schedul':177 'secret':24,56 'secur':160,171 'setup':89,151 'skill':9,29,41,61,77,178,217 'skill-block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard' 'sourc':200,215 'source-agentskillexchange' 'start':167 'status':136 'subscrib':191 'support':67 'suspici':138 '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' 'unsaf':2,34 'upstream':86,111,206 'usag':163 'use':84,152","prices":[{"id":"b6ecc0e1-d87d-4ee2-a354-1e4cac2cad79","listingId":"458bff4f-d077-4206-926f-cecc1bf1d8f4","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":"2026-05-18T13:15:26.086Z"}],"sources":[{"listingId":"458bff4f-d077-4206-926f-cecc1bf1d8f4","source":"github","sourceId":"agentskillexchange/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard","isPrimary":false,"firstSeenAt":"2026-05-18T13:15:26.086Z","lastSeenAt":"2026-05-18T19:09:38.136Z"}],"details":{"listingId":"458bff4f-d077-4206-926f-cecc1bf1d8f4","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard","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":"92a4f329302a001b71d80ccfdf1c9c8543d0c9ca","skill_md_path":"skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Block unsafe agent actions and scan newly added skills with AgentGuard","description":"Add a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/block-unsafe-agent-actions-and-scan-newly-added-skills-with-agentguard"},"updatedAt":"2026-05-18T19:09:38.136Z"}}