ClawHub
Back to skill

Security audit

Mbti Persona

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed MBTI persona preference helper that stores a local OpenClaw configuration file and does not show hidden network, credential, destructive, or privilege behavior.

Install only if you want the agent to adapt its tone and workflow style based on an MBTI profile. Be aware that setting a type creates or updates a persistent local file under ~/.openclaw, so review or remove that file if you no longer want the preference applied.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation guidance includes broad triggers like 'personalized agent behavior' and 'interaction preferences,' which can cause the skill to activate for ordinary conversational requests unrelated to explicit MBTI configuration. Overbroad activation can unexpectedly alter agent behavior or cause configuration changes in contexts where the user did not clearly consent, creating confusion and policy-bypass opportunities through persona shaping.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.