ClawHub
Back to skill

Security audit

Mlscp

Security checks for vulnerabilities and agentic risk

Overview

This skill documents a compact command format for agent communication and does not include executable code or hidden behavior.

Install only if you want a compact protocol reference for agent-to-agent coding commands. Review any MLSCP command that modifies or deletes files before executing it, and note that this package appears to reference supporting scripts and specs that were not included in the inspected artifact.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly documents destructive operations such as file deletion and variable deletion, but it does not include any warning, confirmation guidance, or safety constraints around when these commands should be used. In an agent-to-agent protocol skill, compact destructive commands can lower the friction for unsafe automation and increase the chance that an agent or user invokes irreversible actions without adequate review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.