Back to skill

Security audit

geography-score-improvement

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese high-school geography study skill with no executable code, network payloads, credential handling, or hidden privileged behavior in the inspected artifact.

Before installing, confirm you are comfortable using a Chinese-language education skill and with any wrong-answer or uploaded-question collection being retained for study organization. The package itself contains only Markdown instructions; its claims about large authoritative reference coverage were not verifiable from the shipped files.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is written entirely in Chinese and presents all user interactions and outputs in Chinese-only examples, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation description is broad enough to trigger on many ordinary geography-related queries, which can cause the skill to over-activate outside a narrowly intended scope. In a skill with access to reference materials and workflow features, this increases the chance of inappropriate routing, over-collection of user study data, or responses that bypass better-general handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content is written to operate in Chinese without indicating any language negotiation or fallback behavior. This can lead to incorrect activation or unusable responses for users in other languages, creating reliability and safety issues when users misunderstand educational guidance or cannot verify the output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.