{"id":"ba6e060b-2069-495c-906e-a549b1935d91","shortId":"9Yqd2a","kind":"skill","title":"Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard","tagline":"Screen prompts and responses with input and output scanners before an LLM interaction reaches production users or downstream systems.","description":"# Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard\n\nScreen prompts and responses with input and output scanners before an LLM interaction reaches production users or downstream systems.\n\n## Prerequisites\n\nPython 3.9+, application or agent code that can wrap LLM input and output handling\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install llm-guard\n\nRequirements and caveats from upstream:\n- [![PyPI - Python Version](https://img.shields.io/pypi/v/llm-guard)](https://pypi.org/project/llm-guard)\n- Base functionality requires a limited number of libraries. As you explore more advanced features, necessary libraries\n- Ensure you're using Python version 3.9 or higher. Confirm with: python --version.\n\nBasic usage or getting-started notes:\n- Begin your journey with LLM Guard by downloading the package:\n- sh\n- **Important Notes**:\n\n- Source: https://github.com/protectai/llm-guard\n- Extracted from upstream docs: https://raw.githubusercontent.com/protectai/llm-guard/HEAD/README.md\n\n## Documentation\n\n- https://protectai.github.io/llm-guard/\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard/)","tags":["filter","prompts","and","model","outputs","for","injection","secrets","toxicity","policy","risks","with"],"capabilities":["skill","source-agentskillexchange","skill-filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard","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/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard","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 (1,315 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":"2026-05-18T19:10:28.002Z","embedding":null,"createdAt":"2026-05-18T13:16:33.576Z","updatedAt":"2026-05-18T19:10:28.002Z","lastSeenAt":"2026-05-18T19:10:28.002Z","tsv":"'/llm-guard/':175 '/protectai/llm-guard':164 '/protectai/llm-guard/head/readme.md':171 '/pypi/v/llm-guard)](https://pypi.org/project/llm-guard)':111 '/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard/)':182 '3.9':71,134 'advanc':124 'agent':74,177 'agentskillexchange.com':181 'agentskillexchange.com/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard/)':180 'applic':72 'base':112 'basic':141 'begin':148 'caveat':103 'code':75 'confirm':137 'doc':168 'document':172 'download':155 'downstream':33,67 'ensur':128 'environ':95 'exchang':179 'explor':122 'extract':165 'featur':125 'filter':1,35 'function':113 'get':145 'getting-start':144 'github.com':163 'github.com/protectai/llm-guard':162 'guard':15,49,100,153 'handl':83 'higher':136 'img.shields.io':110 'img.shields.io/pypi/v/llm-guard)](https://pypi.org/project/llm-guard)':109 'import':159 'inject':7,41 'input':21,55,80 'instal':84,88,97 'interact':28,62 'journey':150 'librari':119,127 'limit':116 'llm':14,27,48,61,79,99,152 'llm-guard':98 'match':93 'model':4,38 'necessari':126 'note':147,160 'number':117 'output':5,23,39,57,82 'packag':157 'path':91 'pip':96 'polici':11,45 'prerequisit':69 'product':30,64 'prompt':2,17,36,51 'protectai.github.io':174 'protectai.github.io/llm-guard/':173 'pypi':106 'python':70,107,132,139 'raw.githubusercontent.com':170 'raw.githubusercontent.com/protectai/llm-guard/head/readme.md':169 're':130 'reach':29,63 'requir':101,114 'respons':19,53 'risk':12,46 'scanner':24,58 'screen':16,50 'secret':8,42 'setup':90 'sh':158 'skill':178 'skill-filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard' 'sourc':161,176 'source-agentskillexchange' 'start':146 'system':34,68 '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' 'toxic':9,43 'upstream':87,105,167 'usag':142 'use':85,131 'user':31,65 'version':108,133,140 'wrap':78","prices":[{"id":"cf2e578d-2866-4f60-9301-a87495d1bd07","listingId":"ba6e060b-2069-495c-906e-a549b1935d91","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":"2026-05-18T13:16:33.576Z"}],"sources":[{"listingId":"ba6e060b-2069-495c-906e-a549b1935d91","source":"github","sourceId":"agentskillexchange/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard","isPrimary":false,"firstSeenAt":"2026-05-18T13:16:33.576Z","lastSeenAt":"2026-05-18T19:10:28.002Z"}],"details":{"listingId":"ba6e060b-2069-495c-906e-a549b1935d91","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard","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":"f4ee454759d3340d705b8874bf1f0ec2db7f06f2","skill_md_path":"skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Filter prompts and model outputs for injection, secrets, toxicity, and policy risks with LLM Guard","description":"Screen prompts and responses with input and output scanners before an LLM interaction reaches production users or downstream systems."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/filter-prompts-and-model-outputs-for-injection-secrets-toxicity-and-policy-risks-with-llm-guard"},"updatedAt":"2026-05-18T19:10:28.002Z"}}