input-guard

· v1.0.1

High Risk

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

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

⚠️ Hazard Flags

EXEC PRIVILEGED FS_READ_WORKSPACE FS_READ_USER FS_WRITE_WORKSPACE FS_WRITE_USER FS_DELETE NET_EGRESS_ANY CREDS_ENV CREDS_FILES 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:

SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Prompt injection patterns detected in: SKILL.md high

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

Unauthorized tool use: TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL, INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS critical

Mitigation: Use user-level installs without sudo

Command injection risk: MCP_SCRIPT_TAGS high

Mitigation: Remove embedded script tags and encoded payloads.

Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION low

Mitigation: Provide clear, detailed description of skill functionality

Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_SENSITIVE_DATA) high

Mitigation: Remove references to sensitive data collection.

Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST 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:input-guard:1.0.1",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T02:07:17.885Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "input-guard",
    "version": "1.0.1",
    "format": "agent_skill",
    "description": "Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.",
    "publisher": "ClawHub",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "41762e278f93aae99910e0e88f0464a5eb3401dd5e37372bc5d6ccd388b16689",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "admin",
      "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": true
    },
    "network": {
      "egress": "any",
      "ingress": false
    },
    "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",
      "documents"
    ],
    "content_types": [
      "general"
    ]
  },
  "hazards": {
    "hdac": {
      "H": 4,
      "D": 4,
      "A": 1,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PRIVILEGED",
      "FS_READ_WORKSPACE",
      "FS_READ_USER",
      "FS_WRITE_WORKSPACE",
      "FS_WRITE_USER",
      "FS_DELETE",
      "NET_EGRESS_ANY",
      "CREDS_ENV",
      "CREDS_FILES",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "PROMPT_INJECTION",
        "name": "Prompt Injection Risk",
        "description": "Contains prompt injection patterns in: SKILL.md"
      },
      {
        "code": "PRIVILEGE_ESCALATION",
        "name": "Privilege Escalation",
        "description": "Uses elevated privileges (sudo/root) in: README.md, scripts/scan.py"
      },
      {
        "code": "FILE_DELETE",
        "name": "File Deletion",
        "description": "Can delete files in: README.md, scripts/get_taxonomy.py, SKILL.md"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL, INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS: Attempting to install system packages with elevated privileges"
      },
      {
        "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": "MCP_SCRIPT_TAGS: Script tags, VBScript, or encoded script data URIs"
      },
      {
        "code": "TOOL_POISONING",
        "name": "Tool Poisoning",
        "description": "Hidden secondary behavior detected: MCP_TOOL_POISONING_SENSITIVE_DATA"
      },
      {
        "code": "DATA_EXFILTRATION",
        "name": "Data Exfiltration Risk",
        "description": "DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 8 security patterns (17 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": "Prompt injection patterns detected in: SKILL.md",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL, INSTRUCTED_BINARY_INSTALL, MCP_SYS_FILE_DESTRUCTION, MCP_SYS_CRITICAL_ACCESS",
        "severity": "critical",
        "mitigation": "Use user-level installs without sudo"
      },
      {
        "risk": "Command injection risk: MCP_SCRIPT_TAGS",
        "severity": "high",
        "mitigation": "Remove embedded script tags and encoded payloads."
      },
      {
        "risk": "Social engineering indicators: SOCIAL_ENG_VAGUE_DESCRIPTION, SOCIAL_ENG_ANTHROPIC_IMPERSONATION",
        "severity": "low",
        "mitigation": "Provide clear, detailed description of skill functionality"
      },
      {
        "risk": "Tool poisoning: hidden behaviors detected (MCP_TOOL_POISONING_SENSITIVE_DATA)",
        "severity": "high",
        "mitigation": "Remove references to sensitive data collection."
      },
      {
        "risk": "Data exfiltration patterns: DATA_EXFIL_NETWORK_REQUESTS, DATA_EXFIL_ENV_VARS, DATA_EXFIL_HTTP_POST",
        "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": "evals/run.py",
      "file_path": "evals/run.py"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "_meta.json",
      "file_path": "_meta.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/get_taxonomy.py",
      "file_path": "scripts/get_taxonomy.py"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "scripts/llm_scanner.py",
      "file_path": "scripts/llm_scanner.py"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "scripts/report-to-molthreats.sh",
      "file_path": "scripts/report-to-molthreats.sh"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "scripts/scan.py",
      "file_path": "scripts/scan.py"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "scripts/scan.sh",
      "file_path": "scripts/scan.sh"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "SKILL.md",
      "file_path": "SKILL.md"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL [MEDIUM] README.md:25: sudo apt-get install python3-pip        # Debian/Ubuntu",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "INSTRUCTED_BINARY_INSTALL [HIGH] README.md:26: brew install python3                     # macOS (includes pip)",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "MCP_SYS_FILE_DESTRUCTION [CRITICAL] README.md:241: rm -rf skills/input-guard",
      "file_path": "README.md"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/get_taxonomy.py:15: import requests",
      "file_path": "scripts/get_taxonomy.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] scripts/get_taxonomy.py:28: return os.environ.get(\"PROMPTINTEL_API_KEY\")",
      "file_path": "scripts/get_taxonomy.py"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] scripts/llm_scanner.py:25: import requests",
      "file_path": "scripts/llm_scanner.py"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_HTTP_POST [CRITICAL] scripts/llm_scanner.py:179: response = requests.post(",
      "file_path": "scripts/llm_scanner.py"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] scripts/llm_scanner.py:144: openai_key = os.environ.get(\"OPENAI_API_KEY\")",
      "file_path": "scripts/llm_scanner.py"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] scripts/report-to-molthreats.sh:1: #!/bin/bash",
      "file_path": "scripts/report-to-molthreats.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_TAGS [HIGH] scripts/scan.py:204: (r\"<script[^>]*>\", \"xss_attempt\", Severity.HIGH),",
      "file_path": "scripts/scan.py"
    }
  ]
}