ClawHub
Back to skill

Security audit

Kirklin Typst

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Typst document-template helper that compiles local files and previews PDFs without hidden persistence or unrelated data access.

Install only if you want an agent to create local Typst document copies and run local compilation tools. Review the chosen output path and Typst --root value when compiling sensitive documents, because those control where files are written and what project files Typst can read.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (1)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
// compiles offline with nothing to fetch. It targets the look of the real
// `nips_2017.sty`: Times body + Times-compatible math, a heavy rule / thin rule
// title, bold author names with symbol footnotes (* † ‡), a page-1 venue line,
// and page numbers thereafter. Apply it with a show rule:
//
//   #import "neurips.typ": neurips
//   #show: neurips.with(title: "...", authors: (...), abstract: [...])
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.