Back to skill

Security audit

first-aid-kit

Security checks for vulnerabilities and agentic risk

Overview

This first-aid teaching skill is transparent and mostly scoped, but it contains overgeneralized emergency-care advice that should be reviewed before use.

Review the medical content before installing, especially the CPR and bleeding-control myth corrections. Treat it as educational only, verify advice against current recognized first-aid or emergency-response guidance, and be aware that enabling daily tips creates a recurring scheduled agent message until disabled.

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
Findings (1)

other

Warning
Location
SKILL.md:107
Finding

Unsafe and Overgeneralized Emergency Medical Guidance

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep