ClawHub
Back to skill

Security audit

Advisor

Security checks for vulnerabilities and agentic risk

Overview

This is a simple advice-framing skill with broad scope but no code, persistence, data access, or hidden execution behavior.

Before installing, understand that this skill may be invoked for a wide range of advice-seeking prompts, including finance or major life decisions. Treat its output as structured thinking support rather than professional legal, medical, financial, or mental-health advice.

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
Confidence
93% confidence
Finding
The skill description is extremely broad ('trusted advisor' for business, finance, career, strategy, and major life choices) and overlaps with common user requests for general guidance. This can cause over-invocation or routing capture, where the skill is selected for vague advice-seeking prompts outside a tightly defined scope, increasing the chance of inappropriate authority or unintended handling of sensitive decisions.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The 'When to Use' triggers are ambiguous and map to very common phrases like needing a second opinion or asking 'what would you do in my situation?'. Because these conditions lack scope limits, the skill may activate for a wide range of ordinary conversations, including sensitive or specialized topics where generic advice framing could be unsafe or misleading.

Static analysis

No suspicious patterns detected.