ClawHub
Back to skill

Security audit

Self Improvement Daemon 2ed609

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language guide skill with overly broad triggers, but it contains no code, privileged actions, persistence, or hidden data handling.

Before installing, be aware that this skill may trigger on broad words like "Daemon" or "Tools" and its guidance is in Chinese. It appears safe as a guide-only skill, but users may want narrower activation phrases for better control.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger field contains multiple broad keywords ("self-improvement-daemon / 如何利用DTL / Daemon / Tools") that can match unrelated user requests, especially generic terms like "Daemon" and "Tools". This increases the likelihood of unintended invocation, causing the agent to surface irrelevant or potentially risky instructions outside the narrow intended context of mounting ISO files with Daemon Tools Lite.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The listed trigger scenarios are vague and include broad activation conditions such as users merely mentioning "self-improvement-daemon" or asking for related help. In practice, this can cause the skill to activate in contexts unrelated to ISO mounting, increasing accidental execution and reducing user control over when the skill is invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description, instructions, and trigger scenarios are presented only in Chinese, which can implicitly force a specific language for users without opt-in. The file does not indicate that the skill is intentionally limited to a Chinese-speaking audience or provide an alternative language option.

Content

No source excerpt is available for this finding.