Back to skill

Security audit

Game Dev Sprint Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a game-development sprint planning guide with broad activation phrases but no hidden code, exfiltration, persistence, or privileged behavior.

Installers should expect this skill to help create and maintain sprint planning Markdown files for game development. Consider narrowing the triggers if accidental activation in general software conversations would be disruptive.

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 (2)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
73% confidence
Finding

The phrase "start development" overlaps semantically with generic built-in "start" behavior and is short enough to create command shadowing or ambiguous routing. In systems that prioritize trigger matching, this can invoke the wrong skill or intercept a user command intended for a core workflow, reducing predictability and potentially causing unintended planning or file-creation actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad phrases like "start development," "break down tasks," and "user stories" that are likely to appear in ordinary software conversations outside the intended game-dev sprint context. This can cause unintended auto-activation of the skill, which may steer the agent into creating files, sprint artifacts, or workflow actions when the user did not explicitly request this specific skill.

Content

No source excerpt is available for this finding.