Security audit
selfware
Security checks for vulnerabilities and agentic risk
Overview
This is a protocol-style Markdown skill that describes scoped local file/app behavior with explicit consent requirements for writes, updates, publishing, and outbound discovery.
Before installing, treat this as a protocol/specification skill rather than a narrow task helper. If you use it to build or run a Selfware runtime, review any implementation it generates for the promised boundaries: localhost-only server exposure, writes limited to content/ unless you approve otherwise, no silent remote updates, and explicit consent before sending context or publishing externally.
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.