Back to skill

Security audit

Daily Decision Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese daily-decision helper with no hidden file, network, credential, or persistence behavior; its main issues are broad triggers and vague description.

Install this only if you want a Chinese-language helper for structuring everyday choices. Be aware that its broad triggers may activate during general decision-related chats, and it should not be treated as professional financial, legal, medical, or career advice.

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
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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are extremely generic daily-language terms such as '纠结', '怎么选', and '决策', which are likely to match many unrelated conversations. This can cause the skill to activate unintentionally, intercepting ordinary user requests and potentially displacing more appropriate skills or workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s outputs and user-facing guidance are hardcoded in Chinese across the entire interaction flow, with no language detection, preference setting, or fallback. This can exclude or mislead users who do not read Chinese, increasing the chance of misunderstanding advice in a decision-support context where clarity matters.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description "auto-generated skeleton" is too vague to communicate the skill’s purpose or safe invocation boundaries. This can cause the agent to invoke the skill in inappropriate contexts, increasing the chance of unintended behavior or misuse, though the issue is primarily one of poor specification rather than direct code execution risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

All user-facing instructions and trigger phrases are presented only in Chinese, which can imply a fixed language requirement without documenting user choice. The file does not state that the skill is Chinese-only for a justified regional purpose, nor does it offer language selection.

Content

No source excerpt is available for this finding.