ClawHub
Back to skill

Security audit

MakeMidas

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the scans found no malicious behavior, while noting an unpinned CLI download command as a supply-chain risk.

The scan supports the benign verdict, but it does not make installation risk-free. Before installing, consider whether you are comfortable with the unpinned CLI download and execution; the scan does not identify which package version would run.

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

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 116)May include surrounding context.

md
- Don't generate images of real people without their consent, or content the
  user would not want stored in their MakeMidas account.
- Never print, log or copy tokens, `MAKEMIDAS_API_KEY` or the credentials
  file (`~/.config/makemidas/credentials.json`).
- In ChatGPT, Claude or another MCP client, the MakeMidas MCP server
  (`https://makemidas.com/api/mcp`) does the same without the CLI.

MCP server referenced without pinned version: 'npx -y @makemidas/cli'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The fallback command uses npx -y to download and execute an unpinned npm package without an interactive installation confirmation. A compromised package release could execute with the agent's local permissions and access files or MakeMidas credentials; this is a CLI supply-chain risk, not an unversioned MCP server as the static finding labels it.

Content

No source excerpt is available for this finding.