ClawHub
Back to skill

Security audit

hermoso

Security checks for vulnerabilities and agentic risk

Overview

The skill’s marketing tools and account access fit its stated purpose, with clear controls for activating paid campaigns.

Connect only the accounts you intend to manage, protect the agent key, and specify publishing and spending limits. Prefer the HTTP connection to avoid local npm execution, or pin a reviewed package version. This review covers the supplied instructions, not the external service’s implementation.

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)

MCP server referenced without pinned version: 'npx -y hermoso'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The unversioned npx -y hermoso command can download and execute a changing npm release without an installation confirmation, creating a supply-chain exposure if a future release or the publisher account is compromised. Execution occurs with the agent's local permissions and, in this authentication workflow, access to the supplied API token; this could enable credential theft or unauthorized account actions, although the file provides no evidence of an actual compromise.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.