ClawHub
Back to skill

Security audit

Lead Research Assistant Cn

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward lead-research skill with no executable code, dependencies, persistence, or hidden install behavior.

Installers should treat this as a research assistant: provide product descriptions when possible, and only run it against a repository after checking that secrets, private customer data, and sensitive business files are not being unnecessarily included.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly tells the agent to analyze the user's codebase to understand the product, but it does not warn that repository contents may include proprietary source code, secrets, customer data, or other sensitive business context. In a lead-generation skill, this expands data access beyond what is strictly necessary and can cause unnecessary exposure of confidential information to downstream model processing or external research steps.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The identifier lead-research-assistant-cn and the bilingual description with Chinese trigger phrasing suggest a CN-specific or Chinese-language orientation, but the document does not explain the restriction or offer language/locale selection. Under the policy, forcing or implying a specific language/locale without opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This manifest file describes the skill only in broad functional terms like researching leads, market demand, data mining, competitor analysis, and lead generation, without any explicit trigger phrases, scope limits, or exclusion conditions. In a manifest context, that ambiguity can make it unclear when the skill should activate versus when a more general business or research request should not invoke it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.