Back to skill

Security audit

Comic Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently uses CellCog to generate comics, with ordinary privacy and dependency-installation considerations.

Your prompts and included story material are sent to CellCog, so share only content you are authorized to submit. Review the downloaded base skill and prefer reviewed, pinned dependency versions. This review covers the bundled instructions, not the external SDK or service.

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
  • 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)

The workflow sends user task content to CellCog without an explicit third-party data-sharing warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The usage instructions pass the user's task prompt to CellCog through client.create_chat, potentially including unpublished story ideas, dialogue, and character descriptions. Although CellCog is named as the provider, the file does not explicitly disclose that this content is transmitted to an external service or caution against submitting sensitive material.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The setup command invokes an unpinned npm package through npx and installs skill content without an immutable revision. A compromised upstream release could execute code with the installing user's permissions or introduce malicious agent instructions. The detector's MCP-server label is inaccurate, but the underlying supply-chain risk is valid; installation is conditional rather than part of every generation task.

Content

No source excerpt is available for this finding.