ClawHub
Back to skill

Security audit

Radiology Image Quiz

Security checks for vulnerabilities and agentic risk

Overview

This is a simple text-only radiology quiz helper; its documentation overstates image and interactive features, but I found no hidden access, persistence, network use, or destructive behavior.

Install only if you need a text-based radiology case quiz formatter. Do not expect actual image handling, PDF output, or interactive quiz behavior unless the skill is updated; review any case JSON you provide because the script prints its contents directly.

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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description emphasizes interactive image-based radiology quizzes involving imaging modalities such as X-ray, CT, MRI, and ultrasound. The code, however, only formats and prints text-based quizzes from JSON fields like history, findings, options, answer, and explanation. Although the demo mentions CT in the findings text, there is no image ingestion, rendering, modality-specific processing, or interactive quiz logic. This is a material description-to-behavior mismatch in the core functionality.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Lines L014-L015 say to use the skill for generic academic writing tasks and whenever a documented fallback path is needed. Those conditions are broad and ambiguous, and could cause this skill to be invoked for many non-radiology tasks outside its stated purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest and module docstring describe interactive quiz generation with X-ray, CT, MRI, and ultrasound images, and the file docstring specifically says it generates image-based diagnostic quizzes. However, the implementation only reads JSON text fields like history, findings, options, answer, and explanation, then prints a plain text quiz. There is no image loading, embedding, validation, or interaction logic anywhere in the code.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The top-level docstring explicitly says 'Generate image-based diagnostic quizzes from text descriptions.' The code does not create image-based quizzes at all; it simply concatenates textual case metadata into a printable string. This is an active contradiction between documentation and behavior, not merely omitted detail.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.