Openclaw Skill

· v3.3.5

High Risk

Earn real money creating AI conversations. Agents and humans collaborate as co-equal creators — 80% of subscription revenue goes back to the people who made it worth subscribing to.

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

⚠️ Hazard Flags

EXEC PERSISTENCE FS_READ_USER NET_EGRESS_ANY NET_INGRESS CREDS_ENV CREDS_FILES CREDS_KEYCHAIN ACT_SEND_MESSAGE 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:

APPROVE_SEND: Can send messages
SANDBOX_CONTAINER: Code execution capability

Recommended:

LOG_ACTIONS: Audit trail for all actions

⚡ Risks

Keychain/credential store access in: launchd/README.md high

Mitigation: Block keychain access or use isolated environment.

Prompt injection patterns detected in: launchd/README.md high

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

Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION critical

Mitigation: Avoid accessing system directories unless absolutely necessary.

Command injection risk: MCP_SQL_BLIND, TIRITH_DOTFILE_OVERWRITE high

Mitigation: Remove SQL exploitation patterns.

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 medium

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:impromptu:3.3.5",
    "ssds_version": "0.2.0",
    "scanner_version": "0.4.0+fe6fd9123d50",
    "created_at": "2026-03-05T12:56:06.677Z",
    "created_by": {
      "agent": "safeagentskills-cli/generate-ssds"
    },
    "language": "en",
    "notes": "Auto-generated SSDS. Manual review recommended."
  },
  "skill": {
    "name": "Openclaw Skill",
    "version": "3.3.5",
    "format": "agent_skill",
    "description": "Earn real money creating AI conversations. Agents and humans collaborate as co-equal creators — 80% of subscription revenue goes back to the people who made it worth subscribing to.",
    "publisher": "unknown",
    "source": {
      "channel": "local"
    },
    "artifact": {
      "sha256": "67329cafaea04a82ce43f658a3b52fff38c4b0a989de1d0fb171b95977c9972c",
      "hash_method": "files_sorted"
    }
  },
  "capabilities": {
    "execution": {
      "can_exec_shell": true,
      "can_exec_code": false,
      "privilege_level": "user",
      "can_install_deps": true,
      "can_persist": true
    },
    "filesystem": {
      "reads_workspace": false,
      "reads_user_home": true,
      "reads_system": false,
      "writes_workspace": false,
      "writes_user_home": false,
      "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": true
    },
    "services": [],
    "actions": {
      "can_send_messages": true,
      "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": 3,
      "C": 1
    },
    "flags": [
      "EXEC",
      "PERSISTENCE",
      "FS_READ_USER",
      "NET_EGRESS_ANY",
      "NET_INGRESS",
      "CREDS_ENV",
      "CREDS_FILES",
      "CREDS_KEYCHAIN",
      "ACT_SEND_MESSAGE",
      "PI_WEB",
      "PI_DOCUMENTS"
    ],
    "custom_flags": [
      {
        "code": "CRED_KEYCHAIN",
        "name": "Keychain Access",
        "description": "Accesses system keychain in: launchd/README.md"
      },
      {
        "code": "HIDDEN_INSTRUCTIONS",
        "name": "Hidden Instructions",
        "description": "Contains hidden instructions in comments/invisible chars in: launchd/README.md"
      },
      {
        "code": "PERSISTENCE",
        "name": "Persistence Mechanism",
        "description": "Creates scheduled tasks or startup entries in: heartbeat.py, heartbeat.sh, install.sh, launchd/README.md, systemd/README.md, SKILL.md"
      },
      {
        "code": "NET_INGRESS",
        "name": "Network Server",
        "description": "Listens for incoming connections in: examples/standing-queries.ts"
      },
      {
        "code": "TOOL_ABUSE",
        "name": "Unauthorized Tool Use",
        "description": "MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION: 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": "MCP_SQL_BLIND, TIRITH_DOTFILE_OVERWRITE: Blind SQL injection, system table access, or stored procedure abuse"
      },
      {
        "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: HTTP client library imports that enable external communication"
      }
    ],
    "confidence": {
      "level": "medium",
      "basis": [
        "static_analysis"
      ],
      "notes": "Detected 9 security patterns (14 vendored rule hits). Review recommended."
    },
    "rationale": {
      "H": "H4: Critical: Privilege escalation or malware detected",
      "D": "D4: Critical: Credential theft or data exfiltration",
      "A": "A3: External actions (deploy/message/post)",
      "C": "C1: General content"
    }
  },
  "containment": {
    "level": "maximum",
    "required": [
      {
        "control": "APPROVE_SEND",
        "reason": "Can send messages"
      },
      {
        "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": "Keychain/credential store access in: launchd/README.md",
        "severity": "high",
        "mitigation": "Block keychain access or use isolated environment."
      },
      {
        "risk": "Prompt injection patterns detected in: launchd/README.md",
        "severity": "high",
        "mitigation": "Review SKILL.md for hidden instructions. Do not use with untrusted input."
      },
      {
        "risk": "Unauthorized tool use: MCP_SYS_CRITICAL_ACCESS, TOOL_ABUSE_SYSTEM_MODIFICATION",
        "severity": "critical",
        "mitigation": "Avoid accessing system directories unless absolutely necessary."
      },
      {
        "risk": "Command injection risk: MCP_SQL_BLIND, TIRITH_DOTFILE_OVERWRITE",
        "severity": "high",
        "mitigation": "Remove SQL exploitation patterns."
      },
      {
        "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",
        "severity": "medium",
        "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": "examples/batch-engagement.ts",
      "file_path": "examples/batch-engagement.ts"
    },
    {
      "evidence_id": "EV:file-2",
      "type": "file_excerpt",
      "title": "examples/communities.ts",
      "file_path": "examples/communities.ts"
    },
    {
      "evidence_id": "EV:file-3",
      "type": "file_excerpt",
      "title": "examples/create-conversation.ts",
      "file_path": "examples/create-conversation.ts"
    },
    {
      "evidence_id": "EV:file-4",
      "type": "file_excerpt",
      "title": "examples/discover.ts",
      "file_path": "examples/discover.ts"
    },
    {
      "evidence_id": "EV:file-5",
      "type": "file_excerpt",
      "title": "examples/earnings.ts",
      "file_path": "examples/earnings.ts"
    },
    {
      "evidence_id": "EV:file-6",
      "type": "file_excerpt",
      "title": "examples/full-lifecycle.ts",
      "file_path": "examples/full-lifecycle.ts"
    },
    {
      "evidence_id": "EV:file-7",
      "type": "file_excerpt",
      "title": "examples/heartbeat.ts",
      "file_path": "examples/heartbeat.ts"
    },
    {
      "evidence_id": "EV:file-8",
      "type": "file_excerpt",
      "title": "examples/hiring.ts",
      "file_path": "examples/hiring.ts"
    },
    {
      "evidence_id": "EV:file-9",
      "type": "file_excerpt",
      "title": "examples/manage-credentials.ts",
      "file_path": "examples/manage-credentials.ts"
    },
    {
      "evidence_id": "EV:file-10",
      "type": "file_excerpt",
      "title": "examples/messaging.ts",
      "file_path": "examples/messaging.ts"
    },
    {
      "evidence_id": "EV:cisco-1",
      "type": "file_excerpt",
      "title": "MCP_TOOL_POISONING_SENSITIVE_DATA [HIGH] examples/README.md:82: - Receive and store API key",
      "file_path": "examples/README.md"
    },
    {
      "evidence_id": "EV:cisco-2",
      "type": "file_excerpt",
      "title": "MCP_SQL_BLIND [HIGH] examples/README.md:291: await sleep(error.retryAfter * 1000)",
      "file_path": "examples/README.md"
    },
    {
      "evidence_id": "EV:cisco-3",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_NETWORK_REQUESTS [MEDIUM] heartbeat.py:28: from urllib.request import Request, urlopen",
      "file_path": "heartbeat.py"
    },
    {
      "evidence_id": "EV:cisco-4",
      "type": "file_excerpt",
      "title": "DATA_EXFIL_ENV_VARS [MEDIUM] heartbeat.py:71: api_key = os.environ.get(\"IMPROMPTU_API_KEY\")",
      "file_path": "heartbeat.py"
    },
    {
      "evidence_id": "EV:cisco-5",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] heartbeat.sh:1: #!/bin/bash",
      "file_path": "heartbeat.sh"
    },
    {
      "evidence_id": "EV:cisco-6",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] impromptu-health.sh:1: #!/usr/bin/env bash",
      "file_path": "impromptu-health.sh"
    },
    {
      "evidence_id": "EV:cisco-7",
      "type": "file_excerpt",
      "title": "MCP_SYS_CRITICAL_ACCESS [HIGH] install.sh:1: #!/bin/bash",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-8",
      "type": "file_excerpt",
      "title": "MCP_SCRIPT_ANSI_DECEPTION [HIGH] install.sh:26: RED='\\033[0;31m'",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-9",
      "type": "file_excerpt",
      "title": "TIRITH_ANSI_ESCAPE_IN_STRING [HIGH] install.sh:26: RED='\\033[0;31m'",
      "file_path": "install.sh"
    },
    {
      "evidence_id": "EV:cisco-10",
      "type": "file_excerpt",
      "title": "TOOL_ABUSE_SYSTEM_MODIFICATION [CRITICAL] launchd/README.md:135: chown $USER ~/Library/LaunchAgents/com.impromptu.heartbeat.plist",
      "file_path": "launchd/README.md"
    }
  ]
}