ClawHub
Back to skill

Security audit

IRB Application Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward IRB drafting helper that writes generated documents locally and does not show hidden network, credential, persistence, or destructive behavior.

Before installing, treat this as a drafting aid rather than IRB approval, review all generated content against your institution's requirements, and be aware that generated IRB text is saved locally to the output path.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation text is broad enough to trigger on general research-ethics or human-subjects mentions, even when the user is not clearly requesting IRB application assistance. This can cause inappropriate skill routing, exposing unrelated conversations or causing the agent to produce compliance-oriented outputs in the wrong context.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation summary 'Use when working with irb application assistant' is circular and too vague to constrain when the skill should be invoked. In a sensitive IRB/compliance context, overly broad routing can cause the skill to activate for loosely related research, ethics, or compliance queries, increasing the chance of inappropriate handling of regulated human-subjects content or user overreliance on the wrong workflow.

Description-Behavior Mismatch

Low
Confidence
81% confidence
Finding
The manifest frames the skill as an assistant for drafting informed consent documents, reviewing protocols, generating application forms, and preparing checklists. In code, the tool also persists the generated content to disk by default, which is additional behavior beyond the described assistance functions rather than an obvious requirement of the manifest wording.

Static analysis

No suspicious patterns detected.