Back to skill

Security audit

Xueersi Text Recitation Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact educational recitation helper with no executable code, persistence, credential use, or hidden data access.

This skill appears safe to install for tutoring use. Users should be aware that a few trigger phrases are generic, so the agent may enter recitation-coach mode when a more specific skill trigger would be clearer.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrase "Give me a hint" is highly generic and can easily appear in ordinary conversation unrelated to this skill. In agent environments that activate skills from natural-language matches, this broad phrase increases the chance of accidental invocation, context confusion, or unintended routing into the recitation workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The phrase "Help me remember this text" is ambiguous because it overlaps with normal requests about recalling any prior message or document, not specifically textbook-recitation assistance. This can cause accidental skill triggering or misrouting, especially in multi-skill assistants where "remember" and "text" are common terms.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger "Test me" is extremely generic and likely to appear in many unrelated interactions, making unintended activation particularly plausible. In a shared agent environment, such generic wording can interfere with intent selection and lead to confusing or undesired behavior, even though the underlying skill is educational.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.