ClawHub
Back to skill

Security audit

Email Apology Zh

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language apology email drafting skill with no hidden execution, persistence, network access, or credential handling.

Install this if you want Chinese formal apology email drafting. Review generated text for factual accuracy, legal commitments, compensation terms, and customer-specific details before sending it.

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)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill name includes 'zh' and all descriptive and example content is in Chinese, indicating a Chinese-only behavior. There is no natural-language note offering users a language choice or explaining that the skill is intentionally limited to Chinese-language output.

Vague Triggers

Low
Confidence
85% confidence
Finding
The manifest description broadly states the skill is for many workplace apology scenarios and lists several synonyms, but it does not define clear activation constraints or negative examples. This can make invocation overly broad for general requests involving apologies or delays.

Static analysis

No suspicious patterns detected.