Code Security Auditor

⬇ 188 downloads

High Risk

Comprehensive code security audit with AI-powered vulnerability detection. Covers OWASP Top 10, dependency scanning, secret detection, SAST, and provides actionable fix recommendations. Use when security review, penetration testing, or compliance audit is needed.

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

⚠️ Hazard Flags

EXEC FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER NET_EGRESS_ANY NET_INGRESS 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

Cloud credential access patterns in: test_vulnerable.py high

Mitigation: Verify legitimate need for cloud credential access.

Hardcoded secrets detected in: test_vulnerable.py high

Mitigation: Remove hardcoded secrets. Use environment variables instead.

Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS critical

Mitigation: Remove system modification commands

Command injection risk: COMMAND_INJECTION_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, SQL_INJECTION_STRING_FORMAT critical

Mitigation: Use subprocess with argument lists, not shell strings

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION low

Mitigation: Provide clear, detailed description of skill functionality

Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_SENSITIVE_FILES critical

Mitigation: Ensure network access is necessary and documented

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:code-security-auditor:1.3.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-15T15:12:50.083Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Code Security Auditor",
    "version": "1.3.0",
    "format": "agent_skill",
    "description": "Comprehensive code security audit with AI-powered vulnerability detection. Covers OWASP Top 10, dependency scanning, secret detection, SAST, and provides actionable fix recommendations. Use when security review, penetration testing, or compliance audit is needed.",
    "publisher": "ClawHub",
    "source": {
      "channel": "clawhub",
      "slug": "code-security-auditor",
      "owner": "zenmejiang-commits",
      "downloads": 188,
      "stars": 0
    },
    "artifact": {
      "sha256": "cc22e3200cc43c37d0baba7347d04b5d451e999cabb68714ac52234432e963ae",
      "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": true,
      "reads_system": false,
      "writes_workspace": true,
      "writes_user_home": true,
      "writes_system": false,
      "can_delete": false
    },
    "network": {
      "egress": "any",
      "ingress": true
    },
    "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": 4,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "NET_EGRESS_ANY",
      "NET_INGRESS",
      "CREDS_ENV",
      "CREDS_FILES",
      "PI_WEB"
    ],
    "custom_flags": [
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: test_vulnerable.py"
      },
      {
        "code": "HARDCODED_SECRET",
        "name": "Hardcoded Secrets",
        "description": "Contains hardcoded secrets/API keys in: test_vulnerable.py"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: test_vulnerable.py"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS: Modifying system permissions or configuration"
      },
      {
        "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_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, SQL_INJECTION_STRING_FORMAT: Shell command execution with string formatting (potential injection)"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_SENSITIVE_FILES: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 7 security patterns (20 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "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": "Cloud credential access patterns in: test_vulnerable.py",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Hardcoded secrets detected in: test_vulnerable.py",
        "severity": "high",
        "mitigation": "Remove hardcoded secrets. Use environment variables instead."
      },
      {
        "risk": "Unauthorized tool use: TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, MCP_SYS_PERMISSION_MANIPULATION, MCP_SYS_CRITICAL_ACCESS",
        "severity": "critical",
        "mitigation": "Remove system modification commands"
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_OS_SYSTEM, COMMAND_INJECTION_SHELL_TRUE, SQL_INJECTION_STRING_FORMAT",
        "severity": "critical",
        "mitigation": "Use subprocess with argument lists, not shell strings"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST, DATA_EXFIL_SENSITIVE_FILES",
        "severity": "critical",
        "mitigation": "Ensure network access is necessary and documented"
      }
    ],
    "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": "tests/test_code_security_auditor.py",
      "file_path": "tests/test_code_security_auditor.py"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "test_vulnerable.py",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "README.md",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "llm_integration.py",
      "file_path": "llm_integration.py"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "iterate.sh",
      "file_path": "iterate.sh"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "auditor.py",
      "file_path": "auditor.py"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_OS_SYSTEM [CRITICAL] test_vulnerable.py:40: os.system(f\"ping -c 4 {host}\")",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "COMMAND_INJECTION_SHELL_TRUE [HIGH] test_vulnerable.py:40: os.system(f\"ping -c 4 {host}\")",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "SQL_INJECTION_STRING_FORMAT [CRITICAL] test_vulnerable.py:18: cursor.execute(f\"SELECT * FROM users WHERE id = {user_id}\")",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] test_vulnerable.py:6: import requests",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] test_vulnerable.py:66: API_KEY_SAFE = os.environ.get('API_KEY')",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "SECRET_AWS_KEY [CRITICAL] test_vulnerable.py:23: AWS_ACCESS_KEY = \"AKIAIOSFODNN7EXAMPLE\"",
      "file_path": "test_vulnerable.py"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] SKILL.md:269: chmod 600 .env          # ✅",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] SKILL.md:690: - pip install code-security-auditor",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "SOCIAL_ENG_VAGUE_DESCRIPTION [LOW] SKILL.md:1: ---",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SYS_PERMISSION_MANIPULATION [CRITICAL] SKILL.md:272: chmod 777 anything      # ❌ 禁止",
      "file_path": "SKILL.md"
    }
  ]
}