Back to skill

Security audit

出国留学文书撰写

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent writing assistant for English study-abroad application materials and does not show hidden execution, persistence, or data-exfiltration behavior.

Before installing, expect this skill to help draft English application documents from personal academic information you provide. Review all generated facts, school details, recommender statements, and placeholders before using them, and specify a different language if you do not want English output.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file states '默认使用...正式英文', making English the default output language for the skill. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the skill offers a language choice or clearly documents a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document instructs that the email body should typically be kept to 120–180 English words, which imposes English as the output language. There is no accompanying user choice, opt-in, or justification that this skill is limited to English-language outreach contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown guidance forces a specific language/locale in its natural-language instructions by presenting the skill content only in Chinese. The policy allows locale constraints when they are explicitly justified or when users are given a choice, but neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The section titled '地道英文' instructs the skill to rewrite content into idiomatic English and standardize English usage, but the document does not indicate that this language choice is optional or user-selected. This can violate language/locale policy because it implicitly forces a specific output language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L30 instructs the model to use formal English as the required output language. This is a natural-language locale policy constraint, and the file does not provide an opt-in, alternative language option, or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.