Security audit
repair-or-replace
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local repair-versus-replace calculator and shows no hidden data access, persistence, or unsafe automatic behavior.
This appears reasonable to install for structured repair-or-replace advice. Treat its recommendations as decision support rather than professional repair or safety advice, especially for gas, electrical, vehicle, or other safety-critical items. A minor non-security issue was observed: the script's --help path crashes because of an unescaped percent sign in argparse help text, but normal CLI execution worked during inspection.
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
Static analysis
No suspicious patterns detected.