๐Ÿ›ก๏ธ SafeAgentSkills

lb-nextjs16-skill

ยท v16.1.6

High Risk

Complete Next.js 16 documentation in markdown format. Use when working with Next.js projects, building React applications, configuring routing, data fetching, rendering strategies, deployment, or migrating from other frameworks. Covers App Router, Pages Router, API routes, server components, server actions, caching, and all Next.js features.

H:4 D:4 A:2 C:1

โš ๏ธ Hazard Flags

EXEC CODE_EXEC PRIVILEGED FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_WRITE_SYSTEM NET_EGRESS_ANY NET_INGRESS CREDS_ENV CREDS_FILES CREDS_BROWSER PI_WEB PI_DOCUMENTS

๐Ÿ“‹ Capabilities

Execution

  • โœ… Shell execution
  • โœ… Code execution
  • โŒ Install dependencies
  • โŒ Persistence
  • Privilege: admin

Filesystem

  • โœ… Read workspace
  • โœ… Write workspace
  • โœ… Read home
  • โœ… Write home
  • โŒ Read system
  • โŒ Delete

Network

  • Egress: any
  • โœ… Ingress

Credentials

  • โœ… Environment vars
  • โœ… Credential files
  • โœ… Browser data
  • โŒ Keychain

Actions

โŒ send messagesโŒ post publicโŒ purchaseโŒ transfer moneyโŒ deployโŒ delete external

๐Ÿ”’ Containment

Level: maximum

Required:
  • SANDBOX_CONTAINER: Code execution capability
Recommended:
  • LOG_ACTIONS: Audit trail for all actions

โšก Risks

Base64 decode + execute pattern in: references/01-app/02-guides/progressive-web-apps.mdx critical

Mitigation: Decode and review obfuscated content before use.

Security bypass pattern detected in: references/01-app/02-guides/local-development.mdx critical

Mitigation: This skill attempts to disable security features. Do not use.

Hardcoded secrets detected in: references/01-app/02-guides/environment-variables.mdx high

Mitigation: Remove hardcoded secrets. Use environment variables instead.

Prompt injection patterns detected in: references/01-app/03-api-reference/06-cli/next.mdx, references/02-pages/02-guides/upgrading/version-11.mdx high

Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.

Unauthorized tool use: INSTRUCTED_BINARY_INSTALL high

Mitigation: Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments

Command injection risk: MCP_SCRIPT_TAGS, MCP_SQL_BLIND high

Mitigation: Remove embedded script tags and encoded payloads.

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_REMOTE_STORAGE, MCP_TOOL_POISONING_HIDDEN_ACTIONS) high

Mitigation: Document all remote data storage. Avoid storing sensitive data externally.

Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD high

Mitigation: Document all external data transfers. Remove suspicious upload references.

Want a deeper analysis?

This report was generated by static analysis. Get an LLM-powered deep review with behavioral reasoning and attack surface mapping.

๐Ÿง  Deep Analysis โ€” $5.00

๐Ÿšจ Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

๐Ÿ“„ Raw SSDS JSON click to expand
{
  "meta": {
    "document_id": "ssds:auto:nextjs:16.1.6",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T02:13:20.891Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "lb-nextjs16-skill",
    "version": "16.1.6",
    "format": "agent_skill",
    "description": "Complete Next.js 16 documentation in markdown format. Use when working with Next.js projects, building React applications, configuring routing, data fetching, rendering strategies, deployment, or migrating from other frameworks. Covers App Router, Pages Router, API routes, server components, server actions, caching, and all Next.js features.",
    "publisher": "ClawHub",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "c9c729fd886d6a36f776946be053b5834b2f537abbf05aa9b0ca95d0047b9bf8",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "admin",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": true,
      "can_delete": false
    },
    "network": {
      "egress": "any",
      "ingress": true
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": true,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "code_hosting",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": false,
      "can_post_public": false,
      "can_purchase": false,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": false
    },
    "prompt_injection_surfaces": [
      "web",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 2,
      "C": 1
    },
    "flags": [
      "EXEC",
      "CODE_EXEC",
      "PRIVILEGED",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "NET_EGRESS_ANY",
      "NET_INGRESS",
      "CREDS_ENV",
      "CREDS_FILES",
      "CREDS_BROWSER",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "BASE64_EXEC",
        "name": "Base64 Execute",
        "description": "Decodes and executes obfuscated code in: references/01-app/02-guides/progressive-web-apps.mdx"
      },
      {
        "code": "SECURITY_BYPASS",
        "name": "Security Bypass",
        "description": "Attempts to disable security features in: references/01-app/02-guides/local-development.mdx"
      },
      {
        "code": "CRED_BROWSER",
        "name": "Browser Profile Access",
        "description": "Accesses browser cookies/profiles in: references/01-app/02-guides/memory-usage.mdx, references/01-app/03-api-reference/06-cli/next.mdx"
      },
      {
        "code": "HARDCODED_SECRET",
        "name": "Hardcoded Secrets",
        "description": "Contains hardcoded secrets/API keys in: references/01-app/02-guides/environment-variables.mdx"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: references/01-app/03-api-reference/06-cli/next.mdx, references/02-pages/02-guides/upgrading/version-11.mdx"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: references/01-app/02-guides/local-development.mdx"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: references/01-app/02-guides/custom-server.mdx"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "INSTRUCTED_BINARY_INSTALL: Instructs agent to install external binary or package"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "MCP_SCRIPT_TAGS, MCP_SQL_BLIND: Script tags, VBScript, or encoded script data URIs"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_REMOTE_STORAGE, MCP_TOOL_POISONING_HIDDEN_ACTIONS"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "MCP_EXFIL_EXTERNAL_UPLOAD: Description mentions uploading data to external servers"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 12 security patterns (27 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A2: Service integrations detected",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "control": "SANDBOX_CONTAINER",
        "reason": "Code execution capability"
      }
    ],
    "recommended": [
      {
        "control": "LOG_ACTIONS",
        "reason": "Audit trail for all actions"
      }
    ],
    "uncontained_risk": "Risk level depends on manual review of actual capabilities."
  },
  "risks": {
    "risks": [
      {
        "risk": "Base64 decode + execute pattern in: references/01-app/02-guides/progressive-web-apps.mdx",
        "severity": "critical",
        "mitigation": "Decode and review obfuscated content before use."
      },
      {
        "risk": "Security bypass pattern detected in: references/01-app/02-guides/local-development.mdx",
        "severity": "critical",
        "mitigation": "This skill attempts to disable security features. Do not use."
      },
      {
        "risk": "Hardcoded secrets detected in: references/01-app/02-guides/environment-variables.mdx",
        "severity": "high",
        "mitigation": "Remove hardcoded secrets. Use environment variables instead."
      },
      {
        "risk": "Prompt injection patterns detected in: references/01-app/03-api-reference/06-cli/next.mdx, references/02-pages/02-guides/upgrading/version-11.mdx",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: INSTRUCTED_BINARY_INSTALL",
        "severity": "high",
        "mitigation": "Avoid instructing agents to install arbitrary binaries; bundle dependencies or use sandboxed environments"
      },
      {
        "risk": "Command injection risk: MCP_SCRIPT_TAGS, MCP_SQL_BLIND",
        "severity": "high",
        "mitigation": "Remove embedded script tags and encoded payloads."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_REMOTE_STORAGE, MCP_TOOL_POISONING_HIDDEN_ACTIONS)",
        "severity": "high",
        "mitigation": "Document all remote data storage. Avoid storing sensitive data externally."
      },
      {
        "risk": "Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD",
        "severity": "high",
        "mitigation": "Document all external data transfers. Remove suspicious upload references."
      }
    ],
    "limitations": [
      "Static analysis only - runtime behavior not verified"
    ]
  },
  "incident_response": {
    "kill_switch": [
      "Stop the agent process"
    ],
    "containment": [
      "Review logs for unexpected actions"
    ],
    "recovery": [
      "Depends on skill capabilities"
    ]
  },
  "evidence": [
    {
      "evidence_id": "EV:file-1",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/01-installation.mdx",
      "file_path": "references/01-app/01-getting-started/01-installation.mdx"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/02-project-structure.mdx",
      "file_path": "references/01-app/01-getting-started/02-project-structure.mdx"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/03-layouts-and-pages.mdx",
      "file_path": "references/01-app/01-getting-started/03-layouts-and-pages.mdx"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/04-linking-and-navigating.mdx",
      "file_path": "references/01-app/01-getting-started/04-linking-and-navigating.mdx"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/05-server-and-client-components.mdx",
      "file_path": "references/01-app/01-getting-started/05-server-and-client-components.mdx"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/06-cache-components.mdx",
      "file_path": "references/01-app/01-getting-started/06-cache-components.mdx"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/07-fetching-data.mdx",
      "file_path": "references/01-app/01-getting-started/07-fetching-data.mdx"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "references/01-app/01-getting-started/08-updating-data.mdx",
      "file_path": "references/01-app/01-getting-started/08-updating-data.mdx"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_REMOTE_STORAGE [MEDIUM] references/01-app/02-guides/authentication.mdx:623: > - The payload should contain the **minimum**, unique user data that'll be used",
      "file_path": "references/01-app/02-guides/authentication.mdx"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_HIDDEN_ACTIONS [HIGH] references/01-app/02-guides/caching.mdx:554: For [dynamic segments](/docs/app/api-reference/file-conventions/dynamic-routes) ",
      "file_path": "references/01-app/02-guides/caching.mdx"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/content-security-policy.mdx:191: - Any `<Script>` components using the `nonce` prop",
      "file_path": "references/01-app/02-guides/content-security-policy.mdx"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "SECRET_PRIVATE_KEY [CRITICAL] references/01-app/02-guides/environment-variables.mdx:53: > PRIVATE_KEY=\"-----BEGIN RSA PRIVATE KEY-----",
      "file_path": "references/01-app/02-guides/environment-variables.mdx"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_COERCIVE_HIDDEN_PARAMS [HIGH] references/01-app/02-guides/forms.mdx:109: > - An alternative is to pass arguments as hidden input fields in the form (e.g.",
      "file_path": "references/01-app/02-guides/forms.mdx"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/json-ld.mdx:9: Our current recommendation for JSON-LD is to render structured data as a `<scrip",
      "file_path": "references/01-app/02-guides/json-ld.mdx"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/migrating/app-router-migration.mdx:83: ### `<Script>` Component",
      "file_path": "references/01-app/02-guides/migrating/app-router-migration.mdx"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/migrating/from-create-react-app.mdx:584: - **Optimize third-party scripts** with the [`<Script>` component](/docs/app/gui",
      "file_path": "references/01-app/02-guides/migrating/from-create-react-app.mdx"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/migrating/from-vite.mdx:601: - [Optimize third-party scripts with the `<Script>` component](/docs/app/guides/",
      "file_path": "references/01-app/02-guides/migrating/from-vite.mdx"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] references/01-app/02-guides/production-checklist.mdx:94: - **[`<Script>` Component](/docs/app/guides/scripts):** Optimize third-party scr",
      "file_path": "references/01-app/02-guides/production-checklist.mdx"
    }
  ]
}