ClawHub
Back to skill

Security audit

Agent Fact Check Verify

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed fact-checking skill that mainly guides search and source evaluation, with no evidence of hidden execution, persistence, destructive actions, or data exfiltration.

Install only if you are comfortable with a Traditional Chinese fact-checking workflow that may perform multiple web and social-source searches. Check whether the missing referenced helper files are required for your environment, and avoid using authenticated social CLIs unless you understand what account context they use.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill metadata and content are written entirely in Traditional Chinese and do not indicate any language negotiation or fallback to the user's preferred language. This can cause the agent to respond in a language the user did not request, creating confusion, reducing transparency, and increasing the risk that users misunderstand fact-checking results or safety-relevant caveats.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.