Back to skill

Security audit

1688 Distribution Product Selection Newton

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real 1688 product-search assistant, but it handles account keys and tokens in ways that could expose them.

Review before installing. Use this only with a 1688/OpenClaw account and network environment you trust, avoid the optional ISV token commands until token output is redacted, and prefer a version that restores TLS verification, validates the gateway URL, and stores AK credentials with restrictive permissions.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/_sys/_http.py:141
Finding

Authenticated API Requests Disable TLS Certificate Verification

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/biz/isv_token/cmd.py:27
Finding

ISV Bearer Tokens Are Disclosed in Standard CLI and Agent Output

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/capabilities/configure/service.py:73
Finding

Plaintext Access Key File Is Written Without Enforcing Restrictive Permissions

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
examples/check_env.py:37
Finding

Runtime Installation Uses an Unpinned Third-Party Dependency

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (58)

Tainted flow: 'gateway_url' from os.environ.get (line 33, credential/environment) → requests.patch (network output)

Critical
Category
Data Flow
Confidence
96% confidence
Finding

The code takes OPENCLAW_GATEWAY_URL directly from the environment and sends the API key payload to that URL without validating the scheme, host, or trust boundary. An attacker who can influence the environment can redirect credentials to an arbitrary server, and the default uses plain HTTP, increasing interception and exfiltration risk.

Content

Scanner excerpt · scripts/capabilities/configure/service.py (reported line 50)May include surrounding context.

python
headers = {}
        if token:
            headers["Authorization"] = f"Bearer {token}"
        resp = requests.patch(f"{gateway_url}/api/config",
                              headers=headers, json=payload, timeout=5)
        return resp.ok
    except Exception:

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill routes through a generic CLI interface capable of invoking broader business-domain actions than the stated purpose suggests. Generic command-dispatch patterns can enable unintended action expansion or abuse if the invoked domain/action set is not tightly constrained.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

This file is an environment-check and package-install helper that does not align with the stated 1688 product-selection purpose of the skill. Capability mismatch is dangerous because unrelated scripts in a skill package can hide persistence, staging, or host-modification behavior under the guise of utility code, increasing supply-chain and operator trust risk.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The code can install Python packages by invoking pip through subprocess, which modifies the execution environment and may pull code from external package sources. In the context of a 1688 selection assistant, this behavior is unjustified and increases supply-chain risk, unauthorized environment changes, and the chance of executing unreviewed third-party code.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

This example script collects an AK from the user and configures it through a gateway, which is unrelated to the stated purpose of a product-selection assistant. In a skill whose advertised scope is product search and evaluation, hidden or undocumented credential setup materially increases the risk of credential harvesting, misuse, or unauthorized backend access.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script interactively asks the user to paste an access key and immediately sends it to a configuration function, despite the skill being presented as a selection assistant rather than an authentication or admin utility. That mismatch makes the behavior unjustified in context and dangerous because users may be socially engineered into disclosing sensitive credentials to code they did not expect to handle secrets.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L212 states '所有提示信息使用中文' ('all prompt/output information must use Chinese'), which imposes a fixed language requirement. This is a natural-language policy concern because it does not offer the user a language choice or indicate opt-in for the locale restriction.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill declares broad operational behavior involving shell execution, file reads/writes, environment access, and networked credential workflows, but does not define any explicit tool scope or allowed-tools boundary. That makes the runtime trust model unclear and can permit overbroad capability use, especially because the skill also instructs credential setup and local token storage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

L176-L178 明确要求“所有输出、提示、消息必须使用中文”,这属于语言/locale 强制策略。文档中没有提供用户选择语言的机制,也没有说明该技能仅面向特定中文场景或合规要求,因此符合自然语言政策违规条件。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The docstrings, prompts, and all user-facing output are written in Chinese throughout the script, which imposes a specific language on users without any opt-in or indication that the skill is intended only for a Chinese-speaking context. This matches the policy category for language or locale constraints expressed in natural-language content.

Content

No source excerpt is available for this finding.