ClawHub
Back to skill

Security audit

Habit Quest Logger

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk, text-only habit planning skill with no evidence of hidden data access, persistence, network calls, or destructive behavior.

This skill is suitable if you want a text-only habit planning prompt. It should not be expected to store habits, send reminders, sync data, or enforce accountability; avoid entering sensitive personal details unless you are comfortable sharing them in the chat session.

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
  • 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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises an end-user habit-building tool with specific behavior around quests, daily tiers, streaks, fallback actions, and restart/recovery guidance. The supplied code does something materially different: it acts as a markdown/template reader and formatter for SKILL.md, producing a structured overview of the skill contents and user context. While it states that it performs no external actions, the main mismatch is not permissions but primary purpose: the implementation is effectively a skill introspection/documentation renderer, not a habit-building assistant. Therefore the description does not accurately represent the actual behavior.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises an end-user habit coaching skill focused on building or restarting habits with quest-like structure and recovery guidance. The actual code chunk does not implement that behavior. Instead, it contains tests asserting that metadata and prompt templates load correctly and that the handler returns a descriptive card including sections like Workflow and Output format. This is a materially different primary purpose from habit planning/coaching. There is no evidence here of habit tracking, mission tiers, streak feedback, fallback actions, or missed-day recovery logic. While this may be part of the skill's infrastructure, the supplied code chunk itself does not match the declared functionality.

Content

No source excerpt is available for this finding.

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.

Static analysis

No suspicious patterns detected.