Back to skill

Security audit

拼多多优惠券机器人

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Pinduoduo coupon guidance skill with no executable code, permissions, persistence, or credential access.

Install only if you want Chinese-language Pinduoduo coupon-shopping assistance. Verify any claimed prices, discounts, rebate links, paid plans, or contact channels yourself before spending money, because the skill text describes shopping offers but does not provide a trusted coupon source or enforcement mechanism.

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
88% confidence
Finding

The description claims broad capability across all product categories without meaningful scope boundaries, which increases the chance the orchestrator routes a wide range of ordinary commerce requests into this skill. In context, this is more dangerous because shopping requests are common and highly overlapping, so ambiguous matching can systematically hijack benign user intents.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example trigger phrase is extremely broad for a shopping-domain skill and can match ordinary user shopping requests that are not explicit invocations of this specific tool. That creates over-triggering risk, where the agent may activate the skill unexpectedly, causing inappropriate responses, affiliate-style redirection, or unintended handling of general shopping queries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest text uses Chinese-only natural-language fields (the description and author name) with no indication of language choice or user opt-in. Under the policy for natural-language violations, this can be considered a language/locale constraint that is not documented as optional or region-specific.

Content

No source excerpt is available for this finding.