ClawHub
Back to skill

Security audit

Volcano

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Volcengine summarization guide with disclosed limits and no executable code, though users should be careful around console billing pages.

Install only if you want assistance summarizing Volcengine public pages or user-visible console information. For billing or console pages, keep the session user-directed, do not provide credentials to the agent, and review outputs to ensure account IDs, keys, or other sensitive details are not copied or stored.

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
Confidence
95% confidence
Finding
The invocation description is broad enough to trigger on many ordinary requests related to Volcengine, not just the narrowly intended tasks. Overbroad routing can cause this skill to activate unnecessarily in contexts involving authenticated console access or billing summaries, increasing the chance of unintended data exposure or unsafe automation around sensitive account information.

Static analysis

No suspicious patterns detected.