Back to skill

Security audit

English Speaking & Writing Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed English tutoring skill with Chinese-learner-focused examples and no code, commands, network access, persistence, or credential handling.

Install this if you want English coaching tailored toward Chinese-English transfer, professional writing, speaking practice, and test preparation. If that learner focus does not fit you, ask the agent to adapt the guidance to your own language background instead of applying the Chinese-specific examples by default.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description states the skill is 'Best for Chinese learners,' which imposes a language/locale-targeting preference in the natural-language metadata. The file does not offer users a choice of audience or clarify that the Chinese-learner focus is optional, so this can conflict with language/locale neutrality expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document explicitly targets 'Chinese learners' and frames mistakes as inherent to a specific language group without documenting learner opt-in, necessity, or safeguards. In an educational skill, this can cause unfair profiling, exclusion of users outside the group, and biased personalization decisions if the material is applied broadly or automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The heading 'Pronunciation Tips for Chinese Speakers' explicitly scopes guidance to one language group. Under the policy, language or locale constraints should either be optional or clearly justified; this file does not indicate that users can choose a different language-specific track or that the constraint is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.