{"id":"bada7f6b-36e8-441c-84bf-218c5453cee3","shortId":"MP5Mgb","kind":"skill","title":"Statically scan agent repos for prompt injection and unsafe MCP configs with Agent Audit","tagline":"Audit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping.","description":"# Statically scan agent repos for prompt injection and unsafe MCP configs with Agent Audit\n\nAudit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping.\n\n## Prerequisites\n\nagent-audit, local agent repository or config tree\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install agent-audit\n- git clone https://github.com/HeadyZhang/agent-audit\n\nRequirements and caveats from upstream:\n- [![Python](https://img.shields.io/pypi/pyversions/agent-audit.svg)](https://pypi.org/project/agent-audit/)\n- | T6 | [openai-agents-python](https://github.com/openai/openai-agents-python) | 25 | ASI-01, ASI-02 |\n- | T7 | [adk-python](https://github.com/google/adk-python) | 40 | ASI-02, ASI-04, ASI-10 |\n\nBasic usage or getting-started notes:\n- Install\n- bash\n- Scan your project\n\n- Source: https://github.com/HeadyZhang/agent-audit\n- Extracted from upstream docs: https://raw.githubusercontent.com/HeadyZhang/agent-audit/HEAD/README.md\n\n## Documentation\n\n- https://headyzhang.github.io/agent-audit/\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit/)","tags":["statically","scan","agent","repos","for","prompt","injection","and","unsafe","mcp","configs","with"],"capabilities":["skill","source-agentskillexchange","skill-statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit","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/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit","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 (1,273 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":"2026-05-18T19:12:38.509Z","embedding":null,"createdAt":"2026-05-18T13:19:39.296Z","updatedAt":"2026-05-18T19:12:38.509Z","lastSeenAt":"2026-05-18T19:12:38.509Z","tsv":"'-01':120 '-02':122,132 '-04':134 '-10':136 '/agent-audit/':163 '/google/adk-python)':129 '/headyzhang/agent-audit':100,152 '/headyzhang/agent-audit/head/readme.md':159 '/openai/openai-agents-python)':117 '/pypi/pyversions/agent-audit.svg)](https://pypi.org/project/agent-audit/)':109 '/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit/)':170 '25':118 '40':130 'adk':125 'adk-python':124 'agent':3,13,16,37,47,50,71,74,94,113,165 'agent-audit':70,93 'agentskillexchange.com':169 'agentskillexchange.com/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit/)':168 'asi':119,121,131,133,135 'audit':14,15,48,49,72,95 'bash':145 'basic':137 'caveat':103 'clone':97 'code':17,51 'config':11,45,77 'configur':21,55 'doc':156 'document':160 'environ':90 'exchang':167 'exposur':32,66 'extract':153 'get':141 'getting-start':140 'git':96 'github.com':99,116,128,151 'github.com/google/adk-python)':127 'github.com/headyzhang/agent-audit':98,150 'github.com/openai/openai-agents-python)':115 'headyzhang.github.io':162 'headyzhang.github.io/agent-audit/':161 'img.shields.io':108 'img.shields.io/pypi/pyversions/agent-audit.svg)](https://pypi.org/project/agent-audit/)':107 'inject':7,25,41,59 'instal':79,83,92,144 'issu':28,62 'local':73 'match':88 'mcp':10,20,44,54 'note':143 'openai':112 'openai-agents-python':111 'path':86 'pip':91 'prerequisit':69 'project':148 'prompt':6,18,24,40,52,58 'prompt-inject':23,57 'python':106,114,126 'raw.githubusercontent.com':158 'raw.githubusercontent.com/headyzhang/agent-audit/head/readme.md':157 'repo':4,38 'repositori':75 'requir':101 'scan':2,36,146 'setup':85 'ship':34,68 'skill':166 'skill-statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit' 'sourc':149,164 'source-agentskillexchange' 'start':142 'static':1,35 'surfac':26,60 't6':110 't7':123 'taint':27,61 'tool':31,65 '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' 'tree':78 'unsaf':9,30,43,64 'upstream':82,105,155 'usag':138 'use':80","prices":[{"id":"c6568553-b38b-42c7-862c-50d435ffb911","listingId":"bada7f6b-36e8-441c-84bf-218c5453cee3","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":"2026-05-18T13:19:39.296Z"}],"sources":[{"listingId":"bada7f6b-36e8-441c-84bf-218c5453cee3","source":"github","sourceId":"agentskillexchange/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit","isPrimary":false,"firstSeenAt":"2026-05-18T13:19:39.296Z","lastSeenAt":"2026-05-18T19:12:38.509Z"}],"details":{"listingId":"bada7f6b-36e8-441c-84bf-218c5453cee3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit","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":"b48ca58772d8864a3cd961f4aa8986a47323aa62","skill_md_path":"skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Statically scan agent repos for prompt injection and unsafe MCP configs with Agent Audit","description":"Audit agent code, prompts, and MCP configuration for prompt-injection surfaces, taint issues, and unsafe tool exposure before shipping."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/statically-scan-agent-repos-for-prompt-injection-and-unsafe-mcp-configs-with-agent-audit"},"updatedAt":"2026-05-18T19:12:38.509Z"}}