CLAW Observability

· v1.0.1

High Risk

Real-time visual observability for Claude Code multi-agent workflows. Automatic reporting via hooks — zero agent involvement.

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

⚠️ Hazard Flags

EXEC PERSISTENCE FS_READ_WORKSPACE FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV 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

Pipe-to-shell pattern detected (curl|bash) in: README.md critical

Mitigation: Do not execute. Review source for malicious intent.

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

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_DECEPTION) critical

Mitigation: Remove deceptive language. Tools must be transparent about their behavior.

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:claw-observability:1.0.1",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T15:32:23.369Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "CLAW Observability",
    "version": "1.0.1",
    "format": "agent_skill",
    "description": "Real-time visual observability for Claude Code multi-agent workflows. Automatic reporting via hooks — zero agent involvement.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "48b53c28040b93b0ff9db83a98ff63de5a30b895b90435413d5aa7a96c669fb7",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": true
    },
    "filesystem": {
      "reads_workspace": true,
      "reads_user_home": false,
      "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": 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": [
      "web"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 3,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: README.md"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: README.md, setup.sh"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: README.md"
      },
      {
        "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": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_DECEPTION"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 7 security patterns (7 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": "Pipe-to-shell pattern detected (curl|bash) in: README.md",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "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": "Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_DECEPTION)",
        "severity": "critical",
        "mitigation": "Remove deceptive language. Tools must be transparent about their behavior."
      }
    ],
    "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": "bootstrap.sh",
      "file_path": "bootstrap.sh"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "hooks/claw-hooks.sh",
      "file_path": "hooks/claw-hooks.sh"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "setup.sh",
      "file_path": "setup.sh"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] bootstrap.sh:1: #!/bin/bash",
      "file_path": "bootstrap.sh"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] hooks/claw-hooks.sh:1: #!/bin/bash",
      "file_path": "hooks/claw-hooks.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_DECEPTION [CRITICAL] README.md:48: A chronological trace that shows every agent activation from start to finish. Ev",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] README.md:259: 2. Delete the hook script: `rm -rf ~/.claude/hooks/claw`",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_USER_INPUT [MEDIUM] setup.sh:43: SCRIPT_DIR=\"$(cd \"$(dirname \"$0\")\" && pwd)\"",
      "file_path": "setup.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] setup.sh:1: #!/bin/bash",
      "file_path": "setup.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    }
  ]
}