ClawHub
Back to skill

Security audit

Image Generation

Security checks for vulnerabilities and agentic risk

Overview

The skill’s image-generation workflow fits its stated purpose, with ordinary privacy and dependency-installation considerations.

CellCog processes the prompts and images you submit, so share only material you are authorized to send. Review the separate CellCog dependency and package versions before installation. Its implementation and data-retention practices are not included in this artifact.

A.I.G

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

SkillSpector

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 prompts to CellCog without a privacy warning about third-party data sharing.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The usage instructions submit the user's task prompt to CellCog through create_chat, and the skill also encourages working with existing photos and reference images. Although CellCog is named as the provider, the file does not warn that submitted content is shared with 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
90% confidence
Finding

The suggested npx skills add command can execute an unpinned npm package and retrieve skill content without an explicit immutable revision. A compromised or malicious future release could therefore introduce code or instructions with access to the agent's environment; however, this is an optional installation step, and the finding's description of it as an MCP server is inaccurate.

Content

No source excerpt is available for this finding.