Security audit
laundry-decoder
Security checks for vulnerabilities and agentic risk
Overview
This laundry helper is a coherent offline tool for decoding care labels, planning wash loads, and giving stain advice.
This skill appears safe to install for normal laundry guidance. It runs a local Python command with user-supplied clothing or stain descriptions and does not need credentials or network access; treat its stain and fabric advice as household guidance, not professional dry-cleaning or specialty-material advice.
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
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