ClawHub
Back to skill

Security audit

Finance Digital Avatar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk reference guide for designing compliant financial digital avatars, with no code execution or hidden system access.

This appears safe to install as a reference skill. Users should treat its compliance content as guidance only, verify current legal and regulatory requirements independently, and be aware that broad trigger keywords may make it appear during some general avatar or branding tasks.

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
91% confidence
Finding
The trigger list includes generic phrases such as "brand persona," "AI character," "avatar design," and Chinese terms like "形象设定" and "声音设定," which can appear in ordinary brainstorming or marketing conversations unrelated to this specific skill. The file does not provide boundary conditions, negative examples, or context restrictions explaining when these keywords should or should not invoke the skill.

Static analysis

No suspicious patterns detected.