ClawHub
Back to skill

Security audit

Agent Watcher Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small instruction-only workflow for reading a Moltbook feed and saving selected notes, with one disclosure wording issue about the optional notebook API.

Before installing, keep the Moltbook API key in a secure environment variable, confirm the Open Notebook API URL is local or otherwise trusted, and treat saved notebook/file entries as persistent records of the feed content and your notes.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The security notes are inaccurate: the skill does not only communicate with Moltbook, it can also send collected agent data to a separate Open Notebook API endpoint. This kind of misleading disclosure can cause operators to approve or run the skill under a false understanding of its data flows, especially where localhost services may proxy to synced or externally reachable backends.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.