Back to skill

Security audit

Canva

Security checks for vulnerabilities and agentic risk

Overview

The Canva workflow is clearly described, but its fallback setup runs unverified downloaded code without a separate approval step.

Review before installing. OOMOL will mediate Canva access, and Canva changes require confirmation. Install and verify the CLI yourself before enabling this skill, and review its bundled-skill installation behavior. The concern is uncontrolled setup execution; the inspected artifact does not establish malicious intent.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied chunk performs no visible Canva operations. Instead, it executes an installer from an unrelated domain. Although installing a dependency can be a supporting implementation detail, the supplied code establishes no connection between this installer and the declared Canva functionality. The installer's contents and subsequent effects are not available for assessment.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping the HTTPS response directly into bash executes mutable remote content without integrity verification or review; the PowerShell alternative has the same weakness. A compromised installer host or release pipeline could execute arbitrary code and access local files or credentials, although the supplied content does not establish that the current installer is malicious.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

The setup workflow instructs the agent to execute downloaded installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback setup directs the agent to execute remote installation scripts without requiring separate approval for local software installation or explaining its system effects. Restricting this to a missing-CLI error reduces exposure, but the Canva write-confirmation rules do not cover installation, which could execute arbitrary code with the agent's local privileges.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 88)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources