Back to skill

Security audit

Game Compare Backends

Security checks for vulnerabilities and agentic risk

Overview

This is a small markdown-only game-development workflow for comparing backend choices, with no hidden code, network behavior, persistence, or credential access.

Install this only if you want an agent to spend extra time comparing game backend options and writing a decision note. Expect it to read and update project files for that decision, but the inspected bundle does not contain code execution, credential access, or persistence behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · CHANGELOG.md (reported line 5)May include surrounding context.

md
## 1.1.0 — 2026-03-30

- Initial ClawHub publish bundle generated from `skills/game-compare-backends/SKILL.md`.
- Added bundle metadata, README, and MANIFEST for OpenClaw / ClawHub distribution.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 25)May include surrounding context.

md
## 1.1.0 — 2026-03-30

- Initial ClawHub publish bundle generated from `skills/game-compare-backends/SKILL.md`.
- Added bundle metadata, README, and MANIFEST for OpenClaw / ClawHub distribution.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction says to use the skill on a "fitting game-development task" without defining what counts as fitting or providing constraints or negative examples. This is a broad activation description that could overlap with many ordinary game-development requests and lead to unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The recommended usage bullets describe when to use the skill with phrases like 'for this game project' and 'when the request clearly matches game compare backends,' but they do not define concrete trigger phrases, scope limits, or negative examples. In a markdown skill description, this ambiguity can make invocation criteria too broad and increase the chance of unintended use.

Content

No source excerpt is available for this finding.