ClawHub
Back to skill

Security audit

人物核查

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Cue-based person-check research, but it asks the agent to download or update unpinned remote code and then run it with access to a local Cue API key and paid credits.

Review this before installing if you are not comfortable letting the agent update and run code from the Cue runner repository. Prefer a pinned, trusted checkout of cue-skills, inspect the runner yourself, and confirm credit use only for subjects you intend to research.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to run git pull or git clone into ~/.cue/cue-skills, which modifies the local filesystem and imports untrusted remote code without any integrity verification, pinning, or explicit safety warning. Even though the content is framed as setup for a research runner, this creates a supply-chain and host-modification risk because the fetched repository is later used to execute research_run.py.

Content

No source excerpt is available for this finding.