Security audit

Math Tutor Lite

Security checks for vulnerabilities and agentic risk

Overview

This is a lightweight math tutoring prompt skill with no bundled code or install actions, though it includes an unnecessary promotional fallback message.

Installers should know this skill is prompt-only and appears low risk, but its fallback responses may promote a companion plugin/private workspace even when the user only asked for math help. Review or remove that CTA if neutral tutoring output is required.

A.I.G

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)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:65
Finding: Mandatory Promotional Output Injection in Prompt-Only Tutoring Responses
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation examples are written only in Chinese, and the file does not state that the skill is intentionally limited to Chinese-speaking users or offer multilingual alternatives. This can violate language/locale policy when a skill implicitly constrains activation to a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The 'Use this skill when' section gives a couple of positive examples, but it does not provide negative examples or explicit limits distinguishing single-turn math practice from broader tutoring, homework help, or planning workflows. For markdown files, missing trigger constraints can make routing ambiguous even when the listed examples are reasonably specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.