Back to skill

Security audit

Mbti Coach Suite

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese MBTI coaching router skill with no executable code, network calls, persistence, or credential access, though its repository metadata should be corrected.

This appears safe to install as a guidance-only MBTI coaching skill. Users should treat MBTI advice as reflective coaching rather than psychological assessment, and publishers should fix the mismatched repository metadata before relying on it for source review or provenance.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation conditions are broad enough to match ordinary discussion about personality, self-improvement, or uncertainty, which can trigger the skill outside the user's intended context. Over-broad invocation increases the risk of unsolicited profiling-style guidance and misapplication of MBTI-based advice, especially in ambiguous conversations.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises routing to many specialized coach skills, but most listed targets are not actually published. This can cause broken delegation paths, unreliable behavior, and fallback to improvised in-skill guidance, which increases the chance of inconsistent or hallucinated advice being presented as if it came from validated sub-skills.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest and intro describe this skill as a '轻量级入口' whose role is to help confirm type and guide users to the corresponding specialized coach. However, the document itself includes direct type-classification questions, growth-path summaries, common-error coaching, troubleshooting advice, and example outputs that deliver meaningful coaching content without requiring delegation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description is entirely in Chinese, which indicates a fixed language presentation without any stated user opt-in or locale constraint. Under the policy, language-specific behavior should either offer user choice or clearly document why the locale is required.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest points to a repository URL whose identity appears unrelated to an MBTI coach suite, which creates a software supply chain trust problem. Users and reviewers may rely on the repository for source review, updates, or provenance, and a mismatched link can conceal the real origin of the skill or misdirect auditing.

Content

No source excerpt is available for this finding.