Back to skill

Security audit

teaching-research-analyzer

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly an education helper, but it documents automatic analytics using user identifiers without a clear endpoint, consent, or opt-out.

Review this skill before installing in a school or privacy-sensitive setting. Its teaching analysis behavior is ordinary, but only use it where automatic analytics with user-linked metadata is acceptable or where the host environment can disable or block that tracking.

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
Findings (1)

other

Warning
Location
skill.md:120
Finding

Unverifiable Automatic Telemetry Involving User Identifiers

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation section includes phrases like “帮我分析这道题”, “这道题怎么讲”, and “考点是什么”, which are common educational requests and could match ordinary conversation outside the intended skill-routing context. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The output rules explicitly require “中文输出:分析全部用中文”, which forces a specific language regardless of user preference. This is a natural-language policy concern because no opt-in, fallback, or region-specific justification is provided.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill documentation adds automatic analytics and tracking behavior, including user_id and execution metadata, that is not disclosed in the core manifest purpose of educational analysis. This creates a privacy and transparency risk because users may provide student or teacher content expecting only local pedagogical analysis, while the skill also transmits telemetry to another system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill states that analytics are automatically reported and includes user-related fields, but it does not provide an explicit privacy warning, transmission notice, or consent mechanism. Hidden or insufficiently disclosed data transfer is dangerous because users may unknowingly send identifiable usage metadata alongside educational content.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documented telemetry includes user and runtime fields such as user_id, source, duration, output size, and question type without a clear necessity for the educational analysis function. Over-collection increases privacy exposure and can enable profiling of users' activity patterns, especially in an education context where submitted content may involve minors or sensitive classroom materials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains instructional content only in Chinese, which can amount to forcing a specific language without user opt-in. The policy allows locale constraints when they are explicitly justified or when users are given a choice, neither of which appears in the file.

Content

No source excerpt is available for this finding.