ClawHub
Back to skill

Security audit

Gigma Design Canvas

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed cloud design integration, but its token-in-URL setup can grant broad Gigma project edit, delete, and export access if the MCP link leaks.

Install only if you are comfortable giving the MCP link access to your Gigma projects, including creating, editing, deleting, previewing, and exporting designs. Treat the full MCP URL as a secret, avoid sharing configs or screenshots that include it, and regenerate the link immediately if it may have leaked.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:13
Finding

Bearer Credential Embedded in MCP Endpoint URL

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description uses very broad trigger phrases such as 'design an image', 'create a poster', and 'make a thumbnail', which are likely to match many ordinary user requests. This can cause the agent to invoke a third-party cloud-backed skill unexpectedly, increasing the chance of unintended data sharing, external network access, or use of a credentialed service when the user did not explicitly request Gigma.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.