ClawHub
Back to skill

Security audit

unisound-med-knowledge-qa

Security checks for vulnerabilities and agentic risk

Overview

This medical Q&A skill transparently sends user-provided questions to a disclosed model API and shows no hidden persistence, privilege escalation, or unrelated data access.

Before installing, confirm you are allowed to send the questions you provide to the documented external medical model endpoint. De-identify real patient information, protect the --appkey value, and choose --output paths carefully because outputs can include the original question and metadata.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill documentation exposes capabilities that imply local file read/write and outbound network access, but it does not declare any tool scope or permission boundaries. In an agent environment, this can lead to over-privileged execution where integrators or users cannot easily assess or constrain what the skill may access, increasing the risk of unintended data access or exfiltration.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill states that question content is sent to an internal medical model API, but the general input section does not prominently warn that supplied questions may leave the local host. Because this skill handles medical Q&A and may receive real patient-related text, users could unknowingly transmit sensitive or regulated data to a remote service, creating privacy and compliance risk.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The base system prompt is written to enforce a Chinese-language medical assistant behavior, and the CLI/help text throughout the file is also exclusively Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill sends the full user question and selected metadata to a remote API endpoint, and in this medical context the question may contain sensitive health information, case details, or other regulated data. There is no explicit consent flow, redaction, minimization, or warning before transmission, so users or upstream callers may unknowingly exfiltrate medical data to an external service.

Static analysis

No suspicious patterns detected.