Security audit
agent-builder
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only skill for creating OpenClaw agent workspace files, with no executable payloads or hidden install behavior found.
Before installing, review generated AGENTS.md, HEARTBEAT.md, and MEMORY.md files because they can influence future agent behavior. Keep secrets and session transcripts out of the workspace, and only choose high-autonomy or heartbeat behavior after confirming the generated guardrails match your intent.
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.