ClawHub
Back to skill

Security audit

masheev-cli

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports Masheev workspace tasks, with disclosed access and clear approval steps for customer messages and configuration changes.

Start with read-only access and verify the selected workspace. Approve customer drafts and inspect MCP configuration changes before applying them. Review package versions and any additional skills before installation; the separately downloaded CLI was not audited here.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The documented installer wraps npx skills add masheev/skills without pinning the executable package version or the skill source revision. If invoked, it can execute a newly published or compromised dependency and install changed skill instructions without review. This is a supply-chain exposure rather than an unpinned MCP server, and it is limited to users who invoke this installation path.

Content

No source excerpt is available for this finding.

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 137)May include surrounding context.

masheev skills install # wraps npx skills add masheev/skills

text

`mcp install` points the client at `https://api.masheev.com/api/agents/mcp`
with OAuth and writes no secret; the client then signs in (for example
`codex mcp login masheev`). Show the dry-run diff to the human before
`--write`.

Static analysis

No suspicious patterns detected.