ClawHub
Back to skill

Security audit

Reference Letter

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward writing helper for reference letters with no executable code or hidden access.

Before installing, consider that the skill may draft plausible placeholder examples if you provide limited detail. Review any generated letter carefully, replace marked examples with truthful details, and avoid including sensitive contact or personal information unless needed.

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

Static analysis

No suspicious patterns detected.