Back to skill

Security audit

LLMCOM Prompt Compression

Security checks for vulnerabilities and agentic risk

Overview

This is a simple prompt-compression reference skill with no executable code, sensitive access, persistence, or external data flow.

This skill appears safe to install for manual prompt-compression help. Review compressed prompts before sending them, because removing words and abbreviating terms can lose nuance even though no security-relevant execution or data access is present.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: llmcom
description: Compress prompts for Claude Code and Cursor CLI. Reduces tokens by removing filler words and abbreviating terms. Self-contained, no external dependencies required.
---