Back to skill

Security audit

Game Asset Generation

Security checks for vulnerabilities and agentic risk

Overview

The skill uses CellCog to generate game assets as described, with ordinary privacy and software-installation considerations.

Your game briefs and included project details are sent to CellCog; share only material you are authorized to provide. Review the separate CellCog skill and SDK before installation, and prefer reviewed, pinned versions. The supplied artifact contains only Markdown, which was fully inspected; external dependency behavior remains outside this review.

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

The workflow sends user prompts to CellCog without an explicit data-sharing warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The usage instructions call CellCog's create_chat API with the user's task prompt, transmitting game briefs and any included proprietary details to an external service. Although the skill identifies CellCog as its provider, it does not explicitly warn users that their prompt content leaves the local environment.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The command invokes an unpinned npm CLI through npx and installs skill content from an unpinned repository reference, creating a supply-chain exposure if either upstream is compromised. This is not an MCP server reference as the finding claims, but the underlying reproducibility and code-execution concern is valid; execution still requires following the optional installation instructions.

Content

No source excerpt is available for this finding.