ClawHub
Back to skill

Security audit

harvard-referencing

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Harvard citation-formatting skill with no executable behavior, persistence, credential use, or hidden data access.

Installers should treat this as a narrow referencing aid: confirm the required institutional Harvard variant before use, provide accurate source details, and review the generated citations for consistency and completeness.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Low
Confidence
77% confidence
Finding
The manifest description says "Use for papers requiring Harvard style," which is a general-purpose instruction rather than a narrowly scoped trigger. It does not define explicit invocation phrases, constraints, or negative examples, so the skill could be selected for a wide range of everyday referencing requests beyond the intended context.

Static analysis

No suspicious patterns detected.