ClawHub
Back to skill

Security audit

Canvs.io whiteboard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Canvs.io whiteboard helper with no bundled executable code, but users should be aware that canvas contents are handled by an external service.

Install this if you want Codex to create and modify Canvs.io boards. Avoid sending confidential material unless you are comfortable placing it in a Canvs room, and treat shared room links as potentially accessible to anyone you share them with.

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
  • 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
95% confidence
Finding

The skill description uses broad trigger terms like "draw," "diagram," "sketch," and "visualize anything on a canvas," which can match many ordinary user requests outside the intended Canvs-specific scope. This can cause over-invocation of the skill, leading the agent to route unrelated prompts into an external tool workflow and potentially expose user content or cause unintended actions.

Content

No source excerpt is available for this finding.