ClawHub
Back to skill

Security audit

Assignment Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple assignment-check helper that reads disclosed local course PDF files to summarize deadlines, with privacy caution but no hidden execution or persistence.

Install only if you want an agent to inspect assignment PDFs under /Users/billyshi/Desktop/Waterloo. Confirm the folder is yours and does not contain unrelated sensitive documents before invoking the skill.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description is broad and lacks clear activation boundaries or example triggers, which increases the chance of accidental or overly broad invocation. In this context, broad invocation is risky because the skill is designed to inspect local filesystem content and read PDFs from a user-specific directory, so ambiguous scope can lead to unintended access to private academic files.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs direct access to a hard-coded user-specific local folder and reading PDF assignment files without any user-facing consent, privacy notice, or minimization controls. This is dangerous because it enables silent inspection of local documents that may contain sensitive academic, personal, or identifying information, and the fixed path makes the access behavior broad and automatic rather than explicitly user-scoped.

Static analysis

No suspicious patterns detected.