ClawHub
Back to skill

Security audit

mycroft

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its stated book Q&A purpose, but it installs an unpinned external CLI that will run with access to the user's OpenAI key and local book data.

Review the npm package source and prefer a pinned, audited version before installing. Only provide an OpenAI API key and ebook paths you are comfortable using with this tool, and treat delete commands using --force as confirmation-bypassing data removal.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:5
Finding

Unpinned Third-Party npm Package Creates a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The markdown lists mycroft book delete <id> --force, which performs deletion and explicitly bypasses confirmation, but the surrounding documentation does not warn that this permanently removes indexed book data. For markdown files, safety-impacting behavior that can affect user data should include a clear warning.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.