ClawHub
Back to skill

Security audit

masheev-agent-tuning

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses customer-conversation access and requires owner approval before changing a Masheev agent.

Connect only the intended Masheev workspace with the permissions you need. Customer conversations will be available to your assistant, and approved changes can affect live customer replies. Review proposed changes and retain the original instructions for rollback.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
knowledge changes, and applies them only after the owner approves.
license: Apache-2.0
compatibility: >-
  Requires the Masheev MCP server (https://api.masheev.com/api/agents/mcp,
  streamable HTTP with OAuth) or the masheev CLI. Intended for MCP hosts such as
  ChatGPT, Claude, Codex, Cursor, OpenClaw, Hermes Agent and Grok.
metadata:

Static analysis

No suspicious patterns detected.