ClawHub
Back to skill

Security audit

master-help

Security checks for vulnerabilities and agentic risk

Overview

This is a small routing-only skill that recommends which Buddhist master skill to use and does not request sensitive access or persistent control.

Installers should understand that this skill is only a router: it may read local routing metadata or use a local recommendation command to suggest another master skill. Review its trigger wording if you are sensitive to accidental invocation, but no high-impact or hidden behavior was found.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger description includes broad phrases such as 'help me choose' and '有哪些法师 / which master should I ask' that can match ordinary help-seeking requests far beyond the narrow router purpose. In a skill-routing system, this can cause incorrect invocation of this meta-skill instead of the intended domain skill, leading to misrouting, loss of context, and bypass of more specific safeguards attached to destination skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description embeds Chinese trigger phrases and the skill body is primarily written in Chinese, but there is no explicit statement that language choice follows the user's preference. This can create a locale/language policy concern if the skill defaults to Chinese output or invocation behavior without opt-in.

Content

No source excerpt is available for this finding.