ClawHub
Back to skill

Security audit

Medical Briefs

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward medical research briefing template with no executable code, install hooks, credential handling, or hidden behavior.

Install only if you want an agent to perform web-based medical literature briefings. Treat outputs as research summaries, not medical advice, and verify important clinical claims against the original cited sources.

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
  • 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)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The description and usage criteria are broad enough that the skill may activate for generic requests like 'medical news' or 'research updates' without sufficiently tight specialty or intent constraints. This can cause unintended invocation, leading the agent to fetch and present medical content when the user may have wanted a general answer or a different workflow, increasing the risk of overreach in a medically sensitive domain.

Vague Triggers

Low
Confidence
84% confidence
Finding
The usage examples include phrases like 'Give me today's cardiology brief' and 'Weekly neurology update,' which reinforce ambiguous triggering without defining boundaries between this skill and more general medical-information behaviors. While not overtly dangerous, ambiguous examples can bias routing toward this skill in cases where the user did not explicitly ask for journal-style research briefing.

Static analysis

No suspicious patterns detected.