ClawHub
Back to skill

Security audit

Security Digital Human Ops

Security checks for vulnerabilities and agentic risk

Overview

This is a static guidance skill for financial digital-human content operations, with no executable install or hidden privileged behavior found.

Install only if you want Chinese-market financial digital-human operations guidance. Treat the regulatory tables and compliance claims as planning aids, not legal advice, and verify current requirements with official sources before publishing regulated financial marketing content.

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
94% confidence
Finding
The trigger list is broad and includes generic terms like content creation, short video, live streaming, and brand IP, which can match many ordinary user requests outside the intended banking digital-human scope. This can cause unintended invocation of the skill, leading the agent to apply financial-marketing guidance in irrelevant contexts or without the user's explicit intent.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
Although brief English labels are present, the operational guidance, examples, code comments, and primary instructions are overwhelmingly in Chinese and tailored to Chinese banking regulation. The file does not explicitly state that users may choose their preferred language, which can conflict with a language/locale choice policy unless the locale limitation is clearly documented as region-specific.

Static analysis

No suspicious patterns detected.