Back to skill

Security audit

Project Cookbook Latex

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed document-generation workflow for large technical CookBooks, with no executable payloads or hidden persistence found.

Use this skill when you want a full long-form project CookBook, not for quick documentation edits. Before running it, confirm the exact source paths, remote URLs, output directory, linked skills, and any image upload or network fetching; keep LaTeX shell escape disabled unless the content is trusted and sandboxed.

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
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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The trigger conditions are broad enough to match many ordinary documentation, tutorial, architecture, or book-generation requests, which can cause the skill to activate outside its intended narrow scope. Over-broad invocation increases the chance that the agent performs large-scale content generation, source collection, and linked-skill orchestration when the user only wanted lightweight help, expanding attack surface and enabling unnecessary side effects if later user approval is obtained.

Content

No source excerpt is available for this finding.