Back to skill

Security audit

Game Dev Release

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only game release planning skill with broad triggers, but no hidden execution, persistence, credential access, or destructive behavior.

Installers should be aware that phrases like "release checklist" or "deploy game" may invoke this skill when they intended another release or deploy workflow. Review generated checklists before acting on any store upload, public post, or launch step, and keep actual store submissions manual as the skill itself advises.

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 (3)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
85% confidence
Finding

The skill is heavily themed around 'release', and the trigger phrase 'release checklist' can shadow or interfere with a built-in 'release' command namespace. If the platform matches on prefixes or partial terms, a user trying to invoke a native release/deployment action could be routed into this skill instead, causing command confusion and potentially unsafe workflow execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest lists triggers such as "prepare for release" and "ship my game," which are broad natural-language phrases that could match ordinary conversation beyond a narrowly scoped skill invocation. The file does not provide exclusion conditions or negative examples to clarify when these triggers should or should not activate.

Content

No source excerpt is available for this finding.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding

The trigger 'deploy game' overlaps directly with a built-in 'deploy' command and is more dangerous because this skill explicitly discusses build automation, release builds, and deployment-adjacent actions. In an environment where an agent can run scripts or pipeline steps, shadowing a deployment command could misroute user intent and lead to unintended operational actions or confusion during release handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.