ClawHub
Back to skill

Security audit

[Nyx Archive] Game Design Philosophy

Security checks for vulnerabilities and agentic risk

Overview

This game-design skill is mostly a guidance document, but it asks the agent to passively build a profile of the user's game preferences without clear consent or retention controls.

Review this skill before installing if you do not want an agent to infer and retain your game-design preferences from casual conversation. It should be acceptable only if you are comfortable with adaptive profiling, or if your host environment can keep observations session-only or disable memory for this skill.

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
Findings (1)

other

Warning
Location
SKILL.md:26
Finding

Unbounded Passive User Profiling Without Explicit Consent or Retention Controls

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs itself to passively observe when games come up in conversation and to note detailed user preferences, values, and behavioral patterns, but it provides no consent, retention, minimization, or transparency boundaries. Even without overt exfiltration, this creates unauthorized profiling risk and can normalize covert collection of sensitive preference data over time.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 152)May include surrounding context.

md
- Prototyping philosophy (paper prototype, digital prototype, vertical slice)
- Playtesting practices (when, who, how, what to listen for)
- Technical constraints as creative constraints
- The art of cutting features without cutting soul
- Shipping (done is better than perfect — but perfect is better than bad)

**Key Question:** *"If you had to ship in one week, what would you keep?"*

Static analysis

No suspicious patterns detected.