Security audit

SBTI Test Now

Security checks for vulnerabilities and agentic risk

Overview

This is a self-contained personality test skill that runs local scoring code and bundled questions without hidden network, persistence, or credential behavior.

Installers should understand that this is an entertainment-first personality test, not a clinical assessment. It asks personal preference and relationship-style questions, but the reviewed artifacts do not show data being sent anywhere or stored persistently.

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

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file sets DEFAULT_LANGUAGE = "zh-Hans" and normalize_language silently falls back to that language whenever the requested language is absent or unsupported. This imposes a specific locale by default rather than offering a user choice or clearly documenting a justified region-specific constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The natural-language instructions state the skill should be used to run or re-run the test in Chinese or English, which constrains language handling to specific locales. There is no explicit statement that other language preferences are unsupported by design or that the user is being offered a broader locale choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The file hard-codes supported languages to zh-Hans, zh-Hant, and en, which can result in the skill only operating in those locales. Under the policy rule, language or locale restrictions should either be user-selectable or clearly justified; this file provides the restriction but no visible opt-in or rationale.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.