ClawHub
Back to skill

Security audit

Patient Recruitment Ad Gen

Security checks for vulnerabilities and agentic risk

Overview

This is a local drafting helper for clinical trial recruitment ads, with one minor scoping note but no hidden access, networking, persistence, or credential use.

Before installing, treat this as a drafting aid rather than regulatory approval. Review generated ads with the appropriate IRB/EC, verify all study details against the approved protocol, and avoid entering participant identifiers or unnecessary personal health information.

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

Medium
Confidence
93% confidence
Finding
The 'When to Use' section expands activation beyond clinical-trial ad generation to generic 'academic writing tasks' and 'documented fallback' scenarios. These descriptions are vague and overlap with many unrelated tasks, making it unclear when this skill should activate versus a different writing or reasoning skill.

Static analysis

No suspicious patterns detected.