ClawHub
Back to skill

Security audit

Clinical Trial Protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a plain drafting guide for clinical trial protocol synopses, with clear expert-review and safety caveats and no executable behavior.

This skill is appropriate as a drafting aid, but clinical trial protocols are high-stakes documents. Users should treat outputs as preliminary and require review by qualified investigators, statisticians, IRBs or ethics committees, and applicable regulators before use.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
- [ ] Do not list multiple "primary" endpoints — pick one and demote the rest to secondary
- [ ] Do not let objective, endpoint, and analysis drift apart — they must answer the same question
- [ ] Do not present this as regulatory/statistical sign-off — it's a draft for expert review
- [ ] Do not omit safety monitoring and stopping rules — a protocol without them isn't approvable

## Based On

Static analysis

No suspicious patterns detected.