Knowledge Graph

· v1.1.1

High Risk

"Embedded knowledge graph for persistent structured knowledge. ALWAYS use proactively — do NOT wait for user to ask. Auto-triggers on: (1) any mention of people, projects, devices, services, organizations, or infrastructure — search KG first, add if new, (2) decisions or architectural choices worth remembering, (3) credentials or API keys (store in vault), (4) relationships between entities (who owns what, what runs where, what depends on what), (5) recurring concepts, principles, or lessons learned, (6) preferences and opinions (likes, dislikes, reviews), (7) places and locations (where someone lives, travels, frequents), (8) life events and milestones (birthdays, trips, meetings), (9) habits and routines (daily patterns, recurring behaviors), (10) knowledge artifacts — research papers, articles, insights, ideas, interesting facts shared by the user, (11) know-how and procedures — how to do something, debugging approaches, workflows, mental models, problem-solving frameworks. Also use when recalling facts, answering questions about known entities, or needing structured context. Run install script on first use. NOT for: ephemeral daily notes (use memory/), transient conversation, or rapidly changing data."

H:4 D:3 A:1 C:1

⚠️ Hazard Flags

EXEC CODE_EXEC FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES PI_WEB

📋 Capabilities

Execution

✅ Shell execution
✅ Code execution
❌ Install dependencies
❌ Persistence
Privilege: user

Filesystem

✅ Read workspace
✅ Write workspace
✅ Read home
✅ Write home
❌ Read system
✅ Delete

Network

Egress: any
❌ Ingress

Credentials

✅ Environment vars
✅ Credential files
❌ Browser data
❌ Keychain

Actions

❌ send messages❌ post public❌ purchase❌ transfer money❌ deploy❌ delete external

🔒 Containment

Level: maximum

Required:

SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Command injection risk: COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL, MCP_SCRIPT_TAGS critical

Mitigation: Validate and sanitize all user inputs before using in commands

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_SENSITIVE_DATA) high

Mitigation: Remove references to sensitive data collection.

Want a deeper analysis?

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

🧠 Deep Analysis — $5.00

🚨 Incident Response

Kill switch: Stop the agent process

Containment: Review logs for unexpected actions

Recovery: Depends on skill capabilities

📄 Raw SSDS JSON click to expand

{
  "meta": {
    "document_id": "ssds:auto:knowledge-graph:1.1.1",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:53:50.650Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Knowledge Graph",
    "version": "1.1.1",
    "format": "agent_skill",
    "description": "\"Embedded knowledge graph for persistent structured knowledge. ALWAYS use proactively — do NOT wait for user to ask. Auto-triggers on: (1) any mention of people, projects, devices, services, organizations, or infrastructure — search KG first, add if new, (2) decisions or architectural choices worth remembering, (3) credentials or API keys (store in vault), (4) relationships between entities (who owns what, what runs where, what depends on what), (5) recurring concepts, principles, or lessons learned, (6) preferences and opinions (likes, dislikes, reviews), (7) places and locations (where someone lives, travels, frequents), (8) life events and milestones (birthdays, trips, meetings), (9) habits and routines (daily patterns, recurring behaviors), (10) knowledge artifacts — research papers, articles, insights, ideas, interesting facts shared by the user, (11) know-how and procedures — how to do something, debugging approaches, workflows, mental models, problem-solving frameworks. Also use when recalling facts, answering questions about known entities, or needing structured context. Run install script on first use. NOT for: ephemeral daily notes (use memory/), transient conversation, or rapidly changing data.\"",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "66af079d041931c97421e108857e1eeae796970971a342740d4b102d2fbfdc8a",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "user",
      "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": false,
      "can_delete": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [],
    "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"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 3,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "CODE_EXEC",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/config.mjs"
      },
      {
        "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": "COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL, MCP_SCRIPT_TAGS: User input used in command substitution - potential injection risk"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_SENSITIVE_DATA"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 4 security patterns (5 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D3: Credential access detected",
      "A": "A1: Local side effects only",
      "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": "Command injection risk: COMMAND_INJECTION_USER_INPUT, COMMAND_INJECTION_EVAL, MCP_SCRIPT_TAGS",
        "severity": "critical",
        "mitigation": "Validate and sanitize all user inputs before using in commands"
      },
      {
        "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_SENSITIVE_DATA)",
        "severity": "high",
        "mitigation": "Remove references to sensitive data collection."
      }
    ],
    "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": "lib/config.mjs",
      "file_path": "lib/config.mjs"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "lib/graph.mjs",
      "file_path": "lib/graph.mjs"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "lib/query.mjs",
      "file_path": "lib/query.mjs"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "lib/reader.mjs",
      "file_path": "lib/reader.mjs"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "lib/serialize.mjs",
      "file_path": "lib/serialize.mjs"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "lib/vault.mjs",
      "file_path": "lib/vault.mjs"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "package.json",
      "file_path": "package.json"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/add.mjs",
      "file_path": "scripts/add.mjs"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "scripts/config.mjs",
      "file_path": "scripts/config.mjs"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_SENSITIVE_DATA [HIGH] README.md:43: 5. Stores secrets in the encrypted vault",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/depth-check.mjs:179: console.log('  cd \"$(dirname \"$0\")/..\"  # or cd to workspace root');",
      "file_path": "scripts/depth-check.mjs"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] scripts/validate-kg.mjs:72: while ((m = tickerRe.exec(text)) !== null) {",
      "file_path": "scripts/validate-kg.mjs"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] scripts/visualize.mjs:199: <script>",
      "file_path": "scripts/visualize.mjs"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}