ClawHub
Back to skill

Security audit

codropshipping查看商品

Security checks for vulnerabilities and agentic risk

Overview

This skill uses browser and network access to search CoDropshipping and return product results, with no evidence of hidden code, persistence, credential use, or destructive behavior.

Install only if you want product queries sent to CoDropshipping through browser automation. Avoid using it for confidential sourcing terms unless that disclosure is acceptable, and consider tightening activation phrases if you maintain the skill.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is extremely broad and includes common conversational phrases such as '帮我找' and generic product-category terms, which can cause the skill to activate unintentionally during ordinary user interactions. Because the skill has both network and browser permissions, accidental activation can lead to unanticipated external browsing and data transmission based on user text that was not intended as an explicit product search.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly uses network and browser access to search an external platform, but the description does not disclose that user queries will be sent off-platform or that web automation will occur. This creates a transparency and privacy risk because users may provide commercially sensitive or personal query terms without realizing they are being transmitted to a third-party site.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Line 18 instructs the skill to convert extracted search keywords into English as a fixed behavior. This imposes a language policy on the user's input without opt-in, choice, or an explanation that the target platform requires English queries.

Content

No source excerpt is available for this finding.