{"id":13603,"external_id":"plugin_asdk_app_6af613dd5da881919a31ce59c0dd6816","name":"visionedge-aiscan","display_name":"VisionEdge AIScan","developer":"VisionEdge, s. r. o.","category":"Security","listing_language":"en","listing_language_details":{"method":"cld-0.13.0/listing-v1","reliable":true,"detected_at":"2026-11-16T18:10:08Z","input_sha256":"41c280c083389d31ee1dd307e7360baf3a2c90b4128d51764f1f1d11681ef2e9","source_fields":["release.description","release.interface.short_description","release.interface.long_description"]},"version":"1.7.8","skill_count":2,"first_seen_at":"2026-11-16T18:00:34.189Z","last_seen_at":"2026-11-16T18:00:34.189Z","last_changed_at":"2026-11-16T18:00:34.189Z","install_count":null,"search_matches":[],"research_summary":null,"research_reviewed_at":null,"metadata":{"canonical_app_id":"asdk_app_6af613dd5da881919a31ce59c0dd6816","connector_id":"asdk_app_6af613dd5da881919a31ce59c0dd6816","created_at":"2026-11-12T21:33:21.682014Z","discoverability":"LISTED","id":"plugin_asdk_app_6af613dd5da881919a31ce59c0dd6816","is_template":false,"is_template_instance":false,"name":"visionedge-aiscan","release":{"app_ids":["asdk_app_6af613dd5da881919a31ce59c0dd6816"],"app_manifest":{"apps":{"aiscan":{"id":"asdk_app_6af613dd5da881919a31ce59c0dd6816","required":true}}},"app_templates":[],"description":"Security checks for software written with AI: hallucinated and malicious packages, known vulnerabilities, leaked API keys, unsafe LLM code, open Supabase and Firebase databases, risky agent and MCP settings.","display_name":"VisionEdge AIScan","id":"pluginrel_8bc17a20365c8191a957e210b78582da","interface":{"brand_color":"#2563EB","capabilities":["Detect hallucinated, malicious and typosquatted npm and PyPI packages before installation","Find known vulnerabilities in dependencies with OSV, GitHub advisories, CISA KEV and EPSS","Find hardcoded and browser exposed API keys, always reported redacted","Find unsafe handling of LLM output: eval, shell, SQL, HTML rendering","Check Supabase Row Level Security and Firebase rules","Review MCP server and AI agent configurations for excessive permissions","Detect hidden Unicode instructions in agent rules files","Passive security check of a website the user owns","Newest vulnerabilities in AI frameworks and MCP tooling"],"category":"Security","composer_icon_dark_url":"https://files.openai.com/content?id=file_00000000bbf081f4a2e4ce2d84051694","composer_icon_url":"https://files.openai.com/content?id=file_000000000d9881f4b75c0a6ab4e63d81","default_prompt":"Is the npm package react-codeshift safe to install?","default_prompts":["Is the npm package react-codeshift safe to install?","Check my package.json for hallucinated or vulnerable packages","Scan the code you just wrote for security problems"],"developer_name":"VisionEdge, s. r. o.","logo_url":"https://files.openai.com/content?id=file_00000000f7f881f49418c5b81d935f55","logo_url_dark":"https://files.openai.com/content?id=file_00000000571c81f483288730c2979182","long_description":"AIScan checks software written with AI coding tools for the security mistakes those tools often make.\n\nWhat you can ask:\n- Is a package safe to install? AIScan catches packages that do not exist (AI hallucinations that attackers register with malware, known as slopsquatting), known malicious packages, brand new look-alike packages, typosquats and known vulnerabilities from OSV and GitHub advisories, with the CISA known exploited flag and EPSS exploit probability.\n- Check a whole package.json, requirements.txt, pyproject.toml or lockfile and get the exact upgrades.\n- Scan code you share or that your AI assistant wrote: API keys in code or exposed to the browser (always reported redacted), model output reaching eval, a shell, SQL or HTML, user input inside system prompts, public LLM endpoints without login or rate limits, Supabase tables without Row Level Security, open Firebase rules, risky MCP servers and agent permissions, and hidden Unicode instructions in rules files.\n- Scan a public GitHub repository end to end.\n- Run a passive check of a website you own: HTTPS, security headers, keys inside the JavaScript sent to visitors, public source maps, Supabase and Firebase setup.\n- See the newest vulnerabilities in AI frameworks, LLM SDKs, vector databases and MCP tooling.\n\nEvery finding has a severity, a plain language explanation, the location, a concrete fix and its mapping to the OWASP Top 10 for LLM Applications, the OWASP Top 10 for Agentic Applications and CWE. Code is processed only to answer the request and is not stored.\n\nLimits: AIScan is an automated scanner and cannot prove that software is secure. Website checks are passive and need the user to confirm they own the site or may test it. Deep website checks and live monitoring are available on the AIScan website.","plugin_category_id":"security","privacy_policy_url":"https://aiscan.visionedge.sk/privacy","screenshot_urls":[],"short_description":"Security checks for AI code","terms_of_service_url":"https://aiscan.visionedge.sk/terms","website_url":"https://aiscan.visionedge.sk"},"keywords":["security","slopsquatting","supply chain","vulnerabilities","secrets","owasp llm top 10","mcp","ai agents"],"onboarding_skill_name":"aiscan-onboarding","requires_local_executor":false,"skills":[{"description":"Introduce VisionEdge AIScan to a new user in a few sentences and suggest a first check. Use it the first time the user opens the plugin or asks what AIScan can do.","interface":{"brand_color":null,"default_prompt":null,"display_name":"aiscan-onboarding","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Introduce VisionEdge AIScan to a new user in a few sentences and suggest a first check. Use it the first time the user opens the plugin or asks what AIScan can do."},"name":"aiscan-onboarding","plugin_release_skill_id":"pluginrsk_6af62fdf00bc81918fc022d9a54eb5d7"},{"description":"Check packages, code, repositories and websites for the security mistakes typical of software written with AI, using the VisionEdge AIScan tools. Use it before installing any dependency, after writing code that handles LLM output, secrets, databases or agent tools, and before deploying.","interface":{"brand_color":null,"default_prompt":null,"display_name":"secure-ai-coding","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Check packages, code, repositories and websites for the security mistakes typical of software written with AI, using the VisionEdge AIScan tools. Use it before installing any dependency, after writing code that handles LLM output, secrets, databases or agent tools, and before deploying."},"name":"secure-ai-coding","plugin_release_skill_id":"pluginrsk_6af62fdf5f4081918405c452dd977771"}],"version":"1.7.8"},"scope":"GLOBAL","status":"ENABLED"},"research":null,"package_metadata":{"name":"visionedge-aiscan","author":{"url":"https://visionedge.sk","name":"VisionEdge, s. r. o."},"license":"Proprietary","sources":[{"path":"plugin.json","sha256":"6d464fcb3b3e9a9b63c121db706787020c56df78026facdaddfb5b344c93c57f"},{"path":".codex-plugin/plugin.json","sha256":"66d3687d4c5a18dd0e2b3ccb8727ffa7519f2cf6ddf8f754f3a7e35b7230330e"}],"version":"1.7.8","commerce":false,"homepage":"https://aiscan.visionedge.sk","keywords":["security","slopsquatting","supply chain","vulnerabilities","secrets","owasp llm top 10","mcp","ai agents"],"artifact_id":268460,"observed_at":"2026-11-16T18:17:35Z","support_url":"https://aiscan.visionedge.sk/support","capabilities":["Detect hallucinated, malicious and typosquatted npm and PyPI packages before installation","Find known vulnerabilities in dependencies with OSV, GitHub advisories, CISA KEV and EPSS","Find hardcoded and browser exposed API keys, always reported redacted","Find unsafe handling of LLM output: eval, shell, SQL, HTML rendering","Check Supabase Row Level Security and Firebase rules","Review MCP server and AI agent configurations for excessive permissions","Detect hidden Unicode instructions in agent rules files","Passive security check of a website the user owns","Newest vulnerabilities in AI frameworks and MCP tooling"],"field_sources":{"name":0,"author":0,"license":0,"version":0,"commerce":0,"homepage":0,"keywords":0,"support_url":0,"capabilities":0,"release_notes":0,"onboarding_skill":0,"review_case_counts":0,"availability_countries":0},"release_notes":"First release: package safety checks, dependency file checks, code scanning, public GitHub repository scanning, passive website checks and the AI threat feed.","onboarding_skill":"./skills/aiscan-onboarding/SKILL.md","extraction_version":1,"review_case_counts":{"negative":3,"positive":5},"conflicts_or_errors":[{"field":"keywords","other_source":1},{"field":"capabilities","other_source":1}],"availability_countries":[]}}