Back to skill

Security audit

蜜源返利助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple coupon and rebate assistant skill with no executable code, persistence, credential handling, or hidden behavior.

Before installing, note that the skill may activate on brief mentions of the 蜜源 brand or pinyin name; otherwise it is a disclosed coupon/rebate assistant and does not include code that runs locally or asks for special access.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list contains short, generic phrases such as '蜜源' and 'miyuan' without contextual constraints, which can cause the skill to activate on unrelated conversations. Overly broad activation increases the chance of unintended invocation, causing context hijacking or routing users into commerce flows they did not request.

Content

No source excerpt is available for this finding.