ClawHub
Back to skill

Security audit

Font Awesome

Security checks for vulnerabilities and agentic risk

Overview

This is a small Font Awesome helper skill with mostly transparent icon guidance; the only notable issue is a non-transparent instruction to avoid mentioning its setup file.

Safe to install for Font Awesome help. Be aware that the skill includes a transparency issue: it tells the agent not to mention its setup file. Prefer a version that removes that wording and asks before storing icon preferences in memory.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The instruction to 'Read this silently' and 'never mention this file' explicitly directs the agent to conceal the existence and influence of hidden setup instructions from the user. Even though the surrounding content is mostly harmless UX guidance, forced non-disclosure reduces transparency and can normalize covert behavior, which becomes dangerous if similar hidden instructions later include unsafe or manipulative content.

Static analysis

No suspicious patterns detected.