ClawHub
Back to skill

Security audit

Medical CV/Resume Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple medical CV/resume formatter with some overly broad wording, but I found no hidden access, network use, persistence, credential handling, or destructive behavior.

Install only if you want help formatting medical CVs or resumes, especially for US-style academic medicine materials. Review the output for accuracy and locale fit, because the packaged implementation is basic and does not validate medical credentials, citations, or institution-specific requirements.

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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code does implement a medical CV/resume builder, which aligns with the core subject of the description. However, the declared purpose specifically positions it as a tool for academic writing workflows with structured execution, explicit assumptions, and clear output boundaries. None of those workflow-oriented features or controls are present in the code. Instead, the implementation is a straightforward formatter that assembles education and experience into Markdown and returns it as JSON. This is a materially narrower and somewhat differently framed behavior than declared, so it should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description states that the skill 'Creates medical CVs following US standards,' which imposes a locale-specific standard by default. There is no language explaining user opt-in, region selection, or why the US-only constraint is required.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The 'When to Use' section activates the skill for broad scenarios like 'academic writing workflows' needing structured execution, explicit assumptions, or fallback handling. Those conditions are common across many tasks and do not clearly distinguish when this specific medical CV/resume skill should or should not be invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger text is broad enough that an agent may invoke the skill for loosely related academic-writing tasks without strong scope checks. In this file, that risk is reinforced by the stress-case failure showing the skill can drift outside declared scope and boundary guidance, which can cause inappropriate use in medical/professional document workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This ambiguous trigger lacks clear scope constraints, increasing the chance that the skill is selected for tasks beyond its intended function. Because the audit itself records a boundary-control failure in a stress scenario, the ambiguity is not merely cosmetic; it materially raises the likelihood of misuse or overbroad execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.