ClawHub
Back to skill

Security audit

Voc Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown VOC analysis skill with broad but disclosed analytical scope and no evidence of hidden execution, persistence, credential access, or data exfiltration.

Installers should treat this as a general-purpose VOC/customer-feedback analysis helper. Provide only feedback data you intend the agent to analyze, and be aware that the package references optional guide/script files that are not included in this artifact, which may limit functionality but does not indicate malicious behavior.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description states the skill applies to '任何有"用户/顾客声音"的场景' and can switch to '任何领域', which is very broad for activation scope in a markdown skill description. Without explicit trigger phrases, exclusions, or negative examples, this can cause ambiguous invocation boundaries and overlap with many ordinary analysis requests.

Content

No source excerpt is available for this finding.