ClawHub
Back to skill

Security audit

GKTJ Pt Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a patient survey report generator with disclosed local document-generation behavior and no evidence of hidden, destructive, persistent, or exfiltrating actions.

Before installing, confirm that Chinese patient-facing reports are the intended output and avoid using sensitive patient survey data unless your workspace and retention settings are appropriate. The package appears incomplete because referenced scripts and rule files are not included, so report generation may require missing local files or manual substitutes.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
- Attachment must preserve original question and option meaning.
   - No absolute efficacy or safety claims.

## Required Output Rules
- Patient viewpoint only. Do not rewrite as doctor judgement.
- Do not invent sample size, hospitals, institutions, or dates.
- If sample size or time is missing, use restrained wording and omit unsupported facts.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill mandates report structure using fixed Chinese section headings, which effectively forces a specific language/locale in the generated deliverable. The file does not indicate that users can opt into another language or choose locale-specific output, so this is a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.