openclaw-sec

· v0.2.6

High Risk

AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations

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

⚠️ Hazard Flags

EXEC CODE_EXEC PRIVILEGED PERSISTENCE FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_WRITE_SYSTEM FS_DELETE NET_EGRESS_ANY NET_INGRESS CREDS_ENV CREDS_FILES ACT_PURCHASE ACT_DELETE_EXTERNAL PI_WEB PI_DOCUMENTS

📋 Capabilities

Execution

✅ Shell execution
✅ Code execution
✅ Install dependencies
✅ Persistence
Privilege: admin

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:

APPROVE_PURCHASE: Financial actions possible
SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Pipe-to-shell pattern detected (curl|bash) in: src/modules/command-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/command-injection.ts, tests/zeroleaks-pentest.ts critical

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

Base64 decode + execute pattern in: src/modules/content-scanner/__tests__/scanner.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts critical

Mitigation: Decode and review obfuscated content before use.

Security bypass pattern detected in: hooks/README.md, src/core/__tests__/security-engine.test.ts, __tests__/integration/end-to-end.test.ts critical

Mitigation: This skill attempts to disable security features. Do not use.

SSH key access patterns in: src/modules/path-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, __tests__/integration/multi-module.test.ts high

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

Cloud credential access patterns in: src/modules/path-validator/__tests__/validator.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, src/patterns/secrets/secret-patterns.ts, __tests__/integration/multi-module.test.ts high

Mitigation: Verify legitimate need for cloud credential access.

Hardcoded secrets detected in: SKILL.md, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/secrets/secret-patterns.ts, src/__tests__/benchmarks/performance-benchmark.test.ts, __tests__/integration/multi-module.test.ts high

Mitigation: Remove hardcoded secrets. Use environment variables instead.

Code obfuscation detected in: src/modules/content-scanner/__tests__/scanner.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts medium

Mitigation: Deobfuscate and review code before use.

Prompt injection patterns detected in: README.md, SKILL.md, src/__tests__/benchmarks/performance-benchmark.test.ts, src/core/__tests__/action-engine.test.ts, src/core/__tests__/database-manager.test.ts, src/core/__tests__/security-engine.test.ts, src/modules/prompt-injection/__tests__/detector.test.ts, src/patterns/prompt-injection/instruction-override.ts, src/patterns/prompt-injection/role-manipulation.ts, __tests__/integration/end-to-end.test.ts, __tests__/integration/multi-module.test.ts, __tests__/integration/performance.test.ts, tests/zeroleaks-pentest.ts high

Mitigation: Review SKILL.md for hidden instructions. Do not use with untrusted input.

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

Mitigation: Avoid accessing system directories unless absolutely necessary.

Command injection risk: COMMAND_INJECTION_EVAL, COMMAND_INJECTION_SHELL_TRUE, COMMAND_INJECTION_USER_INPUT, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM, MCP_CMD_NETWORK_TOOLS, TIRITH_PLAIN_HTTP_EXEC, MCP_SQL_TAUTOLOGY, MCP_SCRIPT_TAGS, MCP_SQL_BLIND critical

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

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION low

Mitigation: Provide clear, detailed description of skill functionality

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:openclaw-sec:0.4.0",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T02:22:59.498Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "openclaw-sec",
    "version": "0.2.6",
    "format": "agent_skill",
    "description": "AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violations",
    "publisher": "ClawHub",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "c2a662edd99dc08fdc2bd39c6beed458a0d398330ede9498a95aa1006d13f450",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": true,
      "privilege_level": "admin",
      "can_install_deps": true,
      "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": true
    },
    "network": {
      "egress": "any",
      "ingress": true
    },
    "credentials": {
      "reads_env_vars": true,
      "reads_credential_files": true,
      "reads_browser_data": false,
      "reads_keychain": false
    },
    "services": [
      {
        "service": "email",
        "operations": [
          "read",
          "write"
        ]
      },
      {
        "service": "messaging",
        "operations": [
          "read",
          "write"
        ]
      }
    ],
    "actions": {
      "can_send_messages": false,
      "can_post_public": false,
      "can_purchase": true,
      "can_transfer_money": false,
      "can_deploy": false,
      "can_delete_external": true
    },
    "prompt_injection_surfaces": [
      "web",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 4,
      "C": 1
    },
    "flags": [
      "EXEC",
      "CODE_EXEC",
      "PRIVILEGED",
      "PERSISTENCE",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_WRITE_SYSTEM",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "NET_INGRESS",
      "CREDS_ENV",
      "CREDS_FILES",
      "ACT_PURCHASE",
      "ACT_DELETE_EXTERNAL",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PIPE_TO_SHELL",
        "name": "Pipe to Shell",
        "description": "Downloads and executes remote code (curl|bash pattern) in: src/modules/command-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/command-injection.ts, tests/zeroleaks-pentest.ts"
      },
      {
        "code": "BASE64_EXEC",
        "name": "Base64 Execute",
        "description": "Decodes and executes obfuscated code in: src/modules/content-scanner/__tests__/scanner.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts"
      },
      {
        "code": "SECURITY_BYPASS",
        "name": "Security Bypass",
        "description": "Attempts to disable security features in: hooks/README.md, src/core/__tests__/security-engine.test.ts, __tests__/integration/end-to-end.test.ts"
      },
      {
        "code": "CRED_SSH",
        "name": "SSH Key Access",
        "description": "Accesses SSH keys in: src/modules/path-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, __tests__/integration/multi-module.test.ts"
      },
      {
        "code": "CRED_CLOUD",
        "name": "Cloud Credential Access",
        "description": "Accesses cloud credentials (AWS/GCP/Azure) in: src/modules/path-validator/__tests__/validator.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, src/patterns/secrets/secret-patterns.ts, __tests__/integration/multi-module.test.ts"
      },
      {
        "code": "OBFUSCATED_CODE",
        "name": "Obfuscated Code",
        "description": "Contains obfuscated code patterns in: src/modules/content-scanner/__tests__/scanner.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts"
      },
      {
        "code": "HARDCODED_SECRET",
        "name": "Hardcoded Secrets",
        "description": "Contains hardcoded secrets/API keys in: SKILL.md, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/secrets/secret-patterns.ts, src/__tests__/benchmarks/performance-benchmark.test.ts, __tests__/integration/multi-module.test.ts"
      },
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: README.md, SKILL.md, src/__tests__/benchmarks/performance-benchmark.test.ts, src/core/__tests__/action-engine.test.ts, src/core/__tests__/database-manager.test.ts, src/core/__tests__/security-engine.test.ts, src/modules/prompt-injection/__tests__/detector.test.ts, src/patterns/prompt-injection/instruction-override.ts, src/patterns/prompt-injection/role-manipulation.ts, __tests__/integration/end-to-end.test.ts, __tests__/integration/multi-module.test.ts, __tests__/integration/performance.test.ts, tests/zeroleaks-pentest.ts, src/modules/exfiltration-detector/__tests__/detector.test.ts"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: src/patterns/runtime-validation/path-traversal-patterns.ts"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: src/patterns/prompt-injection/policy-puppetry.ts"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: hooks/legacy/README.md, hooks/README.md, README.md, SKILL.md, src/__tests__/benchmarks/performance-benchmark.test.ts, src/__tests__/cli.test.ts, src/cli.ts, src/core/__tests__/action-engine.test.ts, src/core/__tests__/config-manager.test.ts, src/core/__tests__/database-manager.test.ts, src/core/__tests__/logger.test.ts, src/core/__tests__/security-engine.test.ts, src/core/logger.ts, src/modules/command-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/command-injection.ts, __tests__/integration/end-to-end.test.ts, __tests__/integration/multi-module.test.ts, __tests__/integration/performance.test.ts, tests/zeroleaks-pentest.ts"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: README.md"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION, TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, MCP_SYS_PERMISSION_MANIPULATION: Access to critical system directories"
      },
      {
        "code": "SOCIAL_ENGINEERING",
        "name": "Social Engineering Risk",
        "description": "SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION: Skill description is too vague or missing"
      },
      {
        "code": "COMMAND_INJECTION",
        "name": "Command Injection Risk",
        "description": "COMMAND_INJECTION_EVAL, COMMAND_INJECTION_SHELL_TRUE, COMMAND_INJECTION_USER_INPUT, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM, MCP_CMD_NETWORK_TOOLS, TIRITH_PLAIN_HTTP_EXEC, MCP_SQL_TAUTOLOGY, MCP_SCRIPT_TAGS, MCP_SQL_BLIND: Dangerous code execution functions that can execute arbitrary code"
      },
      {
        "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 16 security patterns (103 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A4: External actions (deploy/message/post)",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "control": "APPROVE_PURCHASE",
        "reason": "Financial actions possible"
      },
      {
        "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: src/modules/command-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/command-injection.ts, tests/zeroleaks-pentest.ts",
        "severity": "critical",
        "mitigation": "Do not execute. Review source for malicious intent."
      },
      {
        "risk": "Base64 decode + execute pattern in: src/modules/content-scanner/__tests__/scanner.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts",
        "severity": "critical",
        "mitigation": "Decode and review obfuscated content before use."
      },
      {
        "risk": "Security bypass pattern detected in: hooks/README.md, src/core/__tests__/security-engine.test.ts, __tests__/integration/end-to-end.test.ts",
        "severity": "critical",
        "mitigation": "This skill attempts to disable security features. Do not use."
      },
      {
        "risk": "SSH key access patterns in: src/modules/path-validator/__tests__/validator.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, __tests__/integration/multi-module.test.ts",
        "severity": "high",
        "mitigation": "Verify legitimate need for SSH access. Consider sandboxing."
      },
      {
        "risk": "Cloud credential access patterns in: src/modules/path-validator/__tests__/validator.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/runtime-validation/path-traversal-patterns.ts, src/patterns/secrets/secret-patterns.ts, __tests__/integration/multi-module.test.ts",
        "severity": "high",
        "mitigation": "Verify legitimate need for cloud credential access."
      },
      {
        "risk": "Hardcoded secrets detected in: SKILL.md, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/secrets/secret-patterns.ts, src/__tests__/benchmarks/performance-benchmark.test.ts, __tests__/integration/multi-module.test.ts",
        "severity": "high",
        "mitigation": "Remove hardcoded secrets. Use environment variables instead."
      },
      {
        "risk": "Code obfuscation detected in: src/modules/content-scanner/__tests__/scanner.test.ts, src/modules/secret-detector/__tests__/detector.test.ts, src/patterns/obfuscation/obfuscation-patterns.ts",
        "severity": "medium",
        "mitigation": "Deobfuscate and review code before use."
      },
      {
        "risk": "Prompt injection patterns detected in: README.md, SKILL.md, src/__tests__/benchmarks/performance-benchmark.test.ts, src/core/__tests__/action-engine.test.ts, src/core/__tests__/database-manager.test.ts, src/core/__tests__/security-engine.test.ts, src/modules/prompt-injection/__tests__/detector.test.ts, src/patterns/prompt-injection/instruction-override.ts, src/patterns/prompt-injection/role-manipulation.ts, __tests__/integration/end-to-end.test.ts, __tests__/integration/multi-module.test.ts, __tests__/integration/performance.test.ts, tests/zeroleaks-pentest.ts",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, MCP_SYS_FILE_DESTRUCTION, TOOL_ABUSE_SYSTEM_MODIFICATION, INSTRUCTED_BINARY_INSTALL, INSTRUCTED_GIT_CLONE_AND_BUILD, MCP_SYS_PERMISSION_MANIPULATION",
        "severity": "critical",
        "mitigation": "Avoid accessing system directories unless absolutely necessary."
      },
      {
        "risk": "Command injection risk: COMMAND_INJECTION_EVAL, COMMAND_INJECTION_SHELL_TRUE, COMMAND_INJECTION_USER_INPUT, MCP_CMD_REVERSE_SHELL, MCP_CMD_DANGEROUS_SYSTEM, MCP_CMD_NETWORK_TOOLS, TIRITH_PLAIN_HTTP_EXEC, MCP_SQL_TAUTOLOGY, MCP_SCRIPT_TAGS, MCP_SQL_BLIND",
        "severity": "critical",
        "mitigation": "Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval()"
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "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": "hooks/install-hooks.sh",
      "file_path": "hooks/install-hooks.sh"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "hooks/legacy/README.md",
      "file_path": "hooks/legacy/README.md"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "hooks/legacy/tool-call-hook.ts",
      "file_path": "hooks/legacy/tool-call-hook.ts"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "hooks/legacy/user-prompt-submit-hook.ts",
      "file_path": "hooks/legacy/user-prompt-submit-hook.ts"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "hooks/README.md",
      "file_path": "hooks/README.md"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "hooks/security-input-validator/handler.ts",
      "file_path": "hooks/security-input-validator/handler.ts"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "hooks/security-tool-validator/handler.ts",
      "file_path": "hooks/security-tool-validator/handler.ts"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "jest.config.js",
      "file_path": "jest.config.js"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.json"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "package.json",
      "file_path": "package.json"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] hooks/install-hooks.sh:1: #!/bin/bash",
      "file_path": "hooks/install-hooks.sh"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] hooks/install-hooks.sh:11: RED='\\033[0;31m'",
      "file_path": "hooks/install-hooks.sh"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] hooks/install-hooks.sh:11: RED='\\033[0;31m'",
      "file_path": "hooks/install-hooks.sh"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] hooks/legacy/README.md:49: rm -rf ~/.claude-code/hooks/user-prompt-submit-hook.ts",
      "file_path": "hooks/legacy/README.md"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] hooks/README.md:179: openclaw hooks test security-input-validator --event command:new --data '{\"input",
      "file_path": "hooks/README.md"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_IGNORE_INSTRUCTIONS [HIGH] README.md:489: - **Instruction Override** (9 patterns) - \"Ignore all previous instructions\", \"f",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_UNRESTRICTED_MODE [HIGH] README.md:490: - **Role Manipulation** (4 patterns) - \"You are now in developer mode\", mode swi",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "PROMPT_INJECTION_REVEAL_SYSTEM [MEDIUM] README.md:493: - **Direct Extraction** (11 patterns) - \"What is your system prompt?\", \"show me ",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] README.md:348: openclaw-sec validate-path \"../../../etc/passwd\"",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:822: run: npm install -g openclaw-sec",
      "file_path": "README.md"
    }
  ]
}