ClawHub
Back to skill

Security audit

Care

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown instruction file, but it describes broad AI-driven medical diagnostics and automated pharmacy actions without clear safety limits or user controls.

Review carefully before installing. This skill should not be used for diagnosis, medication decisions, pharmacy coordination, emergency care, or life-support-related actions unless separate human clinical oversight, explicit consent, privacy controls, and audited integrations are in place.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The content describes continuous biometric telemetry, diagnostics, and automated pharmacy orchestration but does not provide concrete user warnings, safety limitations, or handling requirements for highly sensitive health data and real-world medical actions. Because the skill is positioned in a healthcare and intervention context, omission of explicit consent, verification, and human oversight requirements could lead to privacy harm, unsafe medical automation, or inappropriate trust in AI-generated health actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill’s scope is framed as a definitive, integrated health-intelligence layer for biological and cognitive optimization without clear activation boundaries, permitted actions, or exclusion criteria. In a health-related context, this broad mandate increases the chance of overreach into sensitive medical, biometric, or medication-related decisions, making unsafe invocation and unintended reliance more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.