Back to skill

Security audit

Paper Latex Gen

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only compatibility skill for generating academic LaTeX files, with no hidden code, persistence, network use, or privilege-seeking behavior found.

Before installing, note that this skill appears to be a legacy compatibility entry point. Prefer the documented paper latex command when available, and expect it only to help produce LaTeX paper files.

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

This markdown file documents an old invocation form as latex neurips 2025 深度学习, where latex is a generic term rather than a narrowly scoped command phrase. The document does not provide explicit trigger constraints or negative examples, so the activation wording may collide with ordinary requests about LaTeX rather than this specific skill.

Content

No source excerpt is available for this finding.