Back to skill

Security audit

takeout-decision-fatigue-rescuer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language takeout recommendation skill with no code, persistence, credential use, or hidden high-impact behavior.

Before installing, users should know this skill may activate on broad Chinese phrases about not knowing what to eat and is best suited for Chinese-language takeout decisions. It should not be treated as having direct access to real delivery app inventory unless the agent separately has such data available.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger examples are broad everyday phrases like '不知道吃什么' and '中午吃啥', which can easily appear in casual conversation outside a deliberate request to invoke this skill. This can cause unintended activation, leading the agent to steer the conversation into food-ordering guidance when the user may have meant something else, reducing reliability and potentially exposing contextual data unnecessarily to the skill flow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation section lists general emotional and decision-fatigue states but does not define when the skill should not activate or when clarification is required. Without clear boundaries, the agent may invoke the skill for vague statements about frustration or indecision, causing incorrect workflow selection and a degraded user experience.

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 description, trigger phrases, prompts, and output requirements are written as fixed Chinese-language instructions, with no indication that users may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.