Back to skill

Security audit

Logo Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill uses CellCog for branding work as advertised, with ordinary privacy and dependency-installation considerations.

Your brand brief will be sent to CellCog, so omit unnecessary confidential or personal information. Review dependency versions before installation. The full scanner report and sole bundled artifact were inspected; the separately installed core skill and SDK were not audited here.

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 usage workflow sends user task prompts to CellCog without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs agents to submit the user's task through CellCog's create_chat API. Brand briefs can contain personal information or confidential business strategy, but the skill does not warn that their contents will be transmitted to an external service for processing.

Content

No source excerpt is available for this finding.

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

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The installation command invokes an unpinned npm CLI through npx and references a skill source without an immutable revision, allowing the installed code or instructions to change between runs. A compromised upstream release could execute code with the installing user's privileges or introduce malicious agent instructions; however, the static finding incorrectly describes this as an MCP server reference.

Content

No source excerpt is available for this finding.