{"id":"392d2ea6-4f1b-4f08-8127-0133426f8e62","shortId":"xfyu9Y","kind":"skill","title":"Preflight agent specs for prompt-injection risk across prompt, tool, and architecture layers with Prompt Hardener","tagline":"Describe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.","description":"# Preflight agent specs for prompt-injection risk across prompt, tool, and architecture layers with Prompt Hardener\n\nDescribe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.\n\n## Prerequisites\n\nPython 3, pipx or uv optional\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pipx install https://github.com/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl\n- Recommended if you already use uv for Python tooling.\n- uv tool install https://github.com/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl\n- pip install https://github.com/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl\n\nRequirements and caveats from upstream:\n- **Deterministic first**: init, validate, analyze, report, and diff do not require an LLM API key\n- Use this if you prefer a standard Python environment.\n\nBasic usage or getting-started notes:\n- run deterministic security analysis across prompt, tool, and architecture layers\n- Choose the installation method that fits how you want to use Prompt Hardener.\n- ### Using [pipx](https://pipx.pypa.io/)\n\n- Source: https://github.com/cybozu/prompt-hardener\n- Extracted from upstream docs: https://raw.githubusercontent.com/cybozu/prompt-hardener/HEAD/README.md\n\n## Documentation\n\n- https://github.com/cybozu/prompt-hardener\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener/)","tags":["preflight","agent","specs","for","prompt","injection","risk","across","tool","and","architecture","layers"],"capabilities":["skill","source-agentskillexchange","skill-preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener","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/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener","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 (1,668 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":"2026-05-18T19:11:51.057Z","embedding":null,"createdAt":"2026-05-18T13:18:30.412Z","updatedAt":"2026-05-18T19:11:51.057Z","lastSeenAt":"2026-05-18T19:11:51.057Z","tsv":"'/)':178 '/cybozu/prompt-hardener':182,193 '/cybozu/prompt-hardener/head/readme.md':189 '/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl':94,109,114 '/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener/)':200 '3':73 'across':9,44,155 'agent':2,20,37,55,195 'agent_spec.yaml':22,57 'agentskillexchange.com':199 'agentskillexchange.com/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener/)':198 'alreadi':98 'analysi':28,63,154 'analyz':124 'api':133 'architectur':13,48,159 'basic':144 'caveat':117 'choos':161 'defens':33,68 'describ':18,53 'determinist':24,59,120,152 'diff':127 'doc':186 'document':190 'environ':89,143 'exchang':197 'extract':183 'first':121 'fit':166 'generat':29,64 'get':148 'getting-start':147 'github.com':93,108,113,181,192 'github.com/cybozu/prompt-hardener':180,191 'github.com/cybozu/prompt-hardener/releases/download/v0.6.0/prompt_hardener-0.6.0-py3-none-any.whl':92,107,112 'harden':17,52,173 'init':122 'inject':7,27,42,62 'instal':78,82,91,106,111,163 'key':134 'layer':14,49,160 'llm':132 'match':87 'method':164 'mitig':30,65 'note':150 'option':77 'path':85 'pip':110 'pipx':74,90,175 'pipx.pypa.io':177 'pipx.pypa.io/)':176 'prefer':139 'preflight':1,36 'prerequisit':71 'prompt':6,10,16,26,41,45,51,61,156,172 'prompt-inject':5,25,40,60 'python':72,102,142 'raw.githubusercontent.com':188 'raw.githubusercontent.com/cybozu/prompt-hardener/head/readme.md':187 'recommend':95 'report':125 'requir':115,130 'risk':8,43 'rollout':35,70 'run':23,58,151 'secur':153 'setup':84 'skill':196 'skill-preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener' 'sourc':179,194 'source-agentskillexchange' 'spec':3,38 'standard':141 'start':149 'tool':11,46,103,105,157 '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' 'upstream':81,119,185 'usag':145 'use':79,99,135,171,174 'uv':76,100,104 'valid':32,67,123 'want':169","prices":[{"id":"7c0e8e51-5357-44bc-89ca-98aab4a75a6a","listingId":"392d2ea6-4f1b-4f08-8127-0133426f8e62","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":"2026-05-18T13:18:30.412Z"}],"sources":[{"listingId":"392d2ea6-4f1b-4f08-8127-0133426f8e62","source":"github","sourceId":"agentskillexchange/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener","isPrimary":false,"firstSeenAt":"2026-05-18T13:18:30.412Z","lastSeenAt":"2026-05-18T19:11:51.057Z"}],"details":{"listingId":"392d2ea6-4f1b-4f08-8127-0133426f8e62","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener","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":"e28d84bb161dce724469ef02cabb59494594b164","skill_md_path":"skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Preflight agent specs for prompt-injection risk across prompt, tool, and architecture layers with Prompt Hardener","description":"Describe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/preflight-agent-specs-for-prompt-injection-risk-across-prompt-tool-and-architecture-layers-with-prompt-hardener"},"updatedAt":"2026-05-18T19:11:51.057Z"}}