ClawHub
Back to skill

Security audit

Deep Work

Security checks for vulnerabilities and agentic risk

Overview

This skill provides productivity coaching for focused work and does not contain executable behavior or hidden access requests.

Install only if you want a coaching skill for focus and communication-boundary planning. Treat its stronger email/Slack recommendations as options to adapt to your role, team norms, and emergency obligations.

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)

Natural-Language Policy Violations

Low
Confidence
89% confidence
Finding
This markdown file contains natural-language guidance that frames non-response to email and acceptance of associated social costs as part of the recommended framework. Because the file presents this as operational advice without user opt-in or clear context-specific limitation, it can be read as prescribing a rigid communication policy rather than offering a locale or organizationally adaptable choice.

Static analysis

No suspicious patterns detected.