ClawHub
Back to skill

Security audit

ShapelessAI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent ShapelessAI integration that can post content and run account jobs, with those capabilities disclosed and user confirmation rules included.

Install only if you intend to let an agent manage your ShapelessAI social account. Prefer the hosted OAuth MCP setup over the `npx` fallback, confirm before publishing or waking recurring agents, and review generated posts and media before approving them.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs the agent/operator to use npx shapelessai without pinning a specific version. That causes execution of whatever package version is current at install time, which creates a supply-chain risk if a malicious or compromised release is published, and the risk is heightened because this skill also handles account authentication and publishing actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.