ClawHub
Back to skill

Security audit

Quest Chain Decomposer

Security checks for vulnerabilities and agentic risk

Overview

This is a local productivity-planning skill that turns user-provided goals into structured task plans without hidden access or risky behavior.

Install this if you want structured help breaking goals into steps. It should not need credentials, account access, broad filesystem permissions, or background access; only provide the goal details and constraints you want reflected in the plan.

SkillSpector

Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description says to use the skill when a user 'cannot see the first move,' is 'stalling mid-project,' or needs a task map for 'study, home, admin, or personal projects.' These are very broad situations without clear boundaries or exclusion conditions, which can cause unintended invocation across many ordinary conversations.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The listed conditions such as 'break a goal into a realistic sequence,' 'start today instead of circling the task,' and 're-route after blockers appear' describe common productivity needs that could match many unrelated requests. The file does not provide constraints or non-trigger examples to distinguish this skill from other planning or coaching skills.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
def _load_prompt_template(skill_name):
    return PROMPT_TEMPLATE


def _clean_text(value: Any) -> str:
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.