ClawHub
Back to skill

Security audit

Doc Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Korean-language document workflow that clearly describes creating PDFs and posting linked notifications between Discord channels.

Install only if you want a Korean-language Discord document-posting workflow. Before use, confirm that the source command channel, target channel, document contents, and posting permissions are correct, since the skill is designed to publish files and messages across channels.

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
95% confidence
Finding
The skill advertises broad trigger phrases like '문서 만들어줘', 'PDF 만들어줘', and '리스트 정리해줘', which can match many ordinary user requests and cause the skill to activate outside a narrowly intended workflow. In a skill that generates files and posts across Discord channels, overbroad activation increases the chance of unintended document creation, cross-channel posting, and accidental disclosure or spam.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The natural-language instructions and example outputs are entirely Korean and imply the skill communicates in Korean by default, but there is no statement that users can choose another language or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation.

Static analysis

No suspicious patterns detected.