Back to skill

Security audit

Novai360 跨境电商智能分析

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent external market-analysis integration, but it sends the full execution context to a configurable remote API without clear disclosure or minimization.

Review before installing. Use this skill only if you are comfortable sending market questions and whatever your ClawHub runtime includes in execution context to NOVAI360 or to the configured NOVAI360_API_URL. Do not use it with secrets, credentials, private customer data, confidential strategy documents, or sensitive account information unless the publisher narrows and documents the transmitted fields and validates the API origin.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
index.js:5
Finding

Unrestricted Transmission of Execution Context to a Third-Party API

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
index.js:3
Finding

Unvalidated API Base URL Allows Redirection of Requests to Arbitrary Destinations

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file presents key skill information and security-related updates entirely in Chinese, with no indication that language choice is optional or region-specific. This can violate a language/locale policy when users are not given an explicit language choice or documented justification for the locale constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says the skill integrates LLM and MCP market data services, but it does not clearly warn users that their prompts may be transmitted to external services for processing. This is dangerous because users may enter sensitive business, product, or account-related information under the assumption that analysis is local or private, leading to unintended disclosure to third parties.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill states that it will 'automatically identify intent and call related tools' without defining clear invocation boundaries, approval requirements, or scope limits. In a skill that can access real-time external market data, ambiguous auto-invocation can cause over-broad triggering, unintended external requests, and transmission of user content to third-party services without sufficiently informed user consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill forwards raw input and context to an external API without any visible minimization, consent flow, or disclosure. This can leak sensitive user data, system prompts, credentials embedded in context, or internal metadata to a third party, especially because context is passed wholesale and the destination can be changed via an environment variable.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

With no manifest or documented purpose available, the additional getSkills function appears to enumerate capabilities from a remote service rather than directly perform a narrowly scoped user task. This is a distinct network-backed capability beyond the main chat execution path and is not justified by any stated intent in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

All user-facing instructions and examples are presented in Chinese, and the file does not indicate that the language is optional or limited to a specific regional audience. This can violate language/locale policy when a skill effectively forces one language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The fallback error strings API 调用失败 are hard-coded in Chinese, which imposes a specific language regardless of user preference. This is a natural-language policy concern because the file does not offer any language selection or document a justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest presents the skill name and description only in Chinese, which may impose a language preference without indicating that users can opt into another language or that the skill is intended only for a Chinese-language audience. The policy calls for flagging language or locale constraints when no user choice or justified scope is provided.

Content

No source excerpt is available for this finding.