Security audit

Canvas Design

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly fits a visual-design purpose, but it authorizes arbitrary font downloads and falsely attributes a refinement instruction to the user.

Review this skill before installing. It is aimed at creating visual art files, but you should require explicit approval before any external font download and treat the claimed prior user feedback in the final step as skill guidance, not real conversation history.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:122
Finding: Fabricated User Instruction Directs Unauthorized Agent Behavior
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:108
Finding: Unrestricted Retrieval of Unverified Font Assets
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The invocation criteria are very broad: the skill should be used whenever a user asks for a poster, art, design, or other static piece. That increases the chance the agent routes many underspecified requests into a skill that can create files and, elsewhere in the instructions, perform external downloads, widening attack surface and enabling unexpected side effects from ambiguous prompts.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly authorizes downloading whatever fonts are needed, expanding behavior from local art generation into unrestricted external network retrieval. This creates unnecessary supply-chain and data-exfiltration risk, because remote assets can be malicious, tracking-enabled, license-problematic, or fetched from attacker-influenced sources without user awareness.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill permits downloading external fonts but does not warn users in the description that network access may occur. This reduces informed consent and makes the download behavior harder to anticipate, which is risky when a seemingly local design skill can unexpectedly retrieve remote content.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.