ClawHub
Back to skill

Security audit

Font Interceptor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple font-identification workflow that uses a disclosed third-party website, with a manageable caution around downloaded font files.

Before installing, be aware that target URLs are submitted to MSCHF Font Interceptor and any returned font files come from outside this skill. Verify that you have rights to use downloaded fonts, and treat downloaded TTF/OTF files as untrusted until checked with normal security tooling.

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
Confidence
91% confidence
Finding
The skill directs the agent or user to use a third-party website and then download font files from links it presents, but it provides no warning that this involves an external service or that downloaded files should be treated as untrusted. That creates a supply-chain and user-safety risk: users may be sent to a non-affiliated site, disclose target URLs to that service, and download files without validation or provenance checks.

Static analysis

No suspicious patterns detected.