Back to skill

Security audit

DuoPlus AI

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it asks users to share an API key in conversation, and the scan also flags broad environment and network capabilities without a declared tool scope.

Consider the suspicious verdict and Skillspector’s DO_NOT_INSTALL recommendation before installing. In particular, do not share an API key in conversation or place it in command-line arguments; use a protected credential method if available. The scan was partial because three local references could not be resolved, so the evidence does not cover those references fully.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Tainted flow: 'request' from os.environ.get (line 346, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/duoplus_ai.py (reported line 348)May include surrounding context.

python
self._pace_control_api()
            request = Request(url, data=raw_payload, headers=headers, method="POST")
            try:
                with urlopen(request, timeout=timeout or self.timeout) as response:
                    status = int(response.status)
                    body = response.read()
                try:

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Requires users to disclose an API key in conversation without warning about credential exposure.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The reference requires users to submit an API key through conversation and place it in command-line arguments, exposing it to potentially retained transcripts, tool-call records, and process inspection. Because this credential authorizes cloud-phone management and shell execution, disclosure could enable device access, data compromise, or unauthorized billable operations.

Content

No source excerpt is available for this finding.

Unconditionally sets the API response language to Chinese without user opt-in or justification.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The mandatory headers include Lang: zh, imposing a Chinese locale on all control API calls. The reference provides neither a user language choice nor a documented technical or regional reason for this constraint.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/duoplus_ai.py (reported line 1021)May include surrounding context.

python
("group_id", "group_id"),
            ("proxy_id", "proxy_id"),
        ):
            value = getattr(args, source)
            if value is not None:
                filters[target] = value
        response = client.all_phones(filters) if args.all else client.phones(filters)

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/duoplus_ai.py (reported line 1119)May include surrounding context.

python
"proxy": proxy,
        }
        for name in ("name", "dpi_name", "network_mode", "brand", "model"):
            value = getattr(args, name)
            if value is not None:
                image[name] = value
        _emit(client.control("/api/v1/cloudPhone/initProxy", {"images": [image]}))