Back to skill

Security audit

Decision Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only decision-support skill with no code execution or data access, though users should treat its automatic advice on major life or financial choices cautiously.

Before installing, understand that this skill may proactively offer structured advice when you appear uncertain about important decisions. Use it as a thinking aid, not as a substitute for professional financial, legal, medical, or relationship 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 skill is designed to auto-trigger on broad, common signals like hesitation around important choices, which can cause unsolicited intervention in conversations that only loosely match the intended use case. In a decision-support skill, this creates reliability and safety issues because the assistant may inject structured advice into sensitive topics such as careers, investments, or relationships without clear user consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation logic relies on subjective concepts like whether a situation is a 'decision scenario' or has 'large impact,' leaving too much room for inconsistent or overly aggressive auto-invocation. In practice, this can make the skill activate in ambiguous situations and provide premature guidance on consequential topics, increasing the risk of inappropriate influence or user confusion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The description is authored in both English and Chinese throughout, but the file does not state that language should be selected based on user preference or opt-in. Because policy violations can include forcing a specific language or locale without user choice, the absence of an explicit language-choice instruction is a mild concern.

Content

No source excerpt is available for this finding.