ClawHub
Back to skill

Security audit

Gigma AI Design Canvas

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cloud design-tool integration whose external export behavior is relevant for privacy but fits its stated purpose.

Install this only if you are comfortable using Gigma as a third-party cloud design service. Do not export confidential, proprietary, or sensitive designs unless you accept that the exported PNG will be hosted externally behind a signed URL for 7 days.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly states that exported canvases are uploaded to Google Cloud Storage and returned as signed URLs valid for 7 days, but it does not warn users that design content leaves the local/editor context and becomes externally hosted. This can lead to unintended disclosure of sensitive or proprietary images, marketing assets, or embedded text if users assume export is private or ephemeral only within the tool.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.