Ghostclaw

· v1.0.0

High Risk

Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture, suggesting refactors aligned with tech stack best practices, monitoring repositories for vibe health, or opening PRs with architectural improvements. Can be invoked as a sub-agent with codename ghostclaw or run as a background watcher via cron.

H:4 D:4 A:0 C:1

⚠️ Hazard Flags

EXEC FS_READ_WORKSPACE FS_DELETE CREDS_ENV

📋 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: none
❌ 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

Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION critical

Mitigation: Avoid accessing system directories unless absolutely necessary.

Command injection risk: COMMAND_INJECTION_USER_INPUT medium

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

Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES high

Mitigation: Do not access credential files or sensitive system files

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:ghostclaw:1.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:07:28.732Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Ghostclaw",
    "version": "1.0.0",
    "format": "agent_skill",
    "description": "Architectural code review and refactoring assistant that perceives code vibes and system-level flow issues. Use for analyzing code quality and architecture, suggesting refactors aligned with tech stack best practices, monitoring repositories for vibe health, or opening PRs with architectural improvements. Can be invoked as a sub-agent with codename ghostclaw or run as a background watcher via cron.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "6a56b764c5f5829bbaf9b0900a41f4e67799ab49353ff5fd4f1df7d06029f675",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": false
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": false,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "writes_system": false,
      "can_delete": true
    },
    "network": {
      "egress": "none",
      "ingress": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": false,
      "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": [],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 0,
      "C": 1
    },
    "flags": [
      "EXEC",
      "FS_READ_WORKSPACE",
      "FS_DELETE",
      "CREDS_ENV"
    ],
    "custom_flags": [
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: scripts/watcher.sh"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION: Access to critical system directories"
      },
      {
        "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: User input used in command substitution - potential injection risk"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_SENSITIVE_FILES: Accessing sensitive system or credential files"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 5 security patterns (7 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A0: No side effects 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": "Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION",
        "severity": "critical",
        "mitigation": "Avoid accessing system directories unless absolutely necessary."
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_USER_INPUT",
        "severity": "medium",
        "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": "Data exfiltration patterns: DATA_EXFIL_SENSITIVE_FILES",
        "severity": "high",
        "mitigation": "Do not access credential files or sensitive system files"
      }
    ],
    "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": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "scripts/analyze.py",
      "file_path": "scripts/analyze.py"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "scripts/ghostclaw.sh",
      "file_path": "scripts/ghostclaw.sh"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/install.sh",
      "file_path": "scripts/install.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/watcher.sh",
      "file_path": "scripts/watcher.sh"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/analyze.py:20: with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:",
      "file_path": "scripts/analyze.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/ghostclaw.sh:1: #!/usr/bin/env bash",
      "file_path": "scripts/ghostclaw.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] scripts/install.sh:19: cp -r \"$(dirname \"$0\")/..\" \"$SKILLS_DIR/ghostclaw\"",
      "file_path": "scripts/install.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/install.sh:1: #!/usr/bin/env bash",
      "file_path": "scripts/install.sh"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] scripts/watcher.sh:61: trap 'rm -rf \"$tmpdir\"' EXIT",
      "file_path": "scripts/watcher.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/watcher.sh:1: #!/usr/bin/env bash",
      "file_path": "scripts/watcher.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}