Back to skill

Security audit

user-need-miner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese-language product research helper, with the main caution that it may search public web sources for user-need analysis if the user provides no data.

Before installing, use this skill for product research where web collection is acceptable, and give it clear limits on sources, geography, language, and whether identifiable personal posts should be excluded. Prefer user-supplied or aggregated data for sensitive topics.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding

The invocation description uses broad trigger terms like 用户需求、用户画像、需求分析、用户调研、痛点分析 without narrowing scope, which can cause the skill to activate on loosely related prompts and collect or infer user data in contexts the user did not clearly intend. In a skill designed to mine needs from interviews, reviews, and social content, overbroad routing increases the chance of unnecessary profiling or analysis of sensitive user-provided material.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to use WebSearch to collect public information when no raw data is provided, but gives no warning about external data access, consent boundaries, source reliability, or privacy implications. Because this skill builds user profiles and demand analyses from social posts, reviews, and forums, the lack of provenance and privacy controls can lead to unauthorized aggregation of personal data, inaccurate profiling, and use of low-quality or legally problematic sources.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill name, description, headings, examples, and output conventions are all presented in Chinese, and there is no indication that users may choose another language. This creates a natural-language locale constraint without opt-in or justification that the skill is region-specific.

Content

No source excerpt is available for this finding.