Security audit
Everwood AIDLC (OpenClaw)
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed local planning workflow that writes approval/session notes in the workspace and uses reviewer subagents only for gated review.
Install only if you want a structured planning gate before non-trivial coding work. Be aware it will create local aidlc-sessions files in each workspace and may spawn read-only reviewer subagents; avoid putting secrets, credentials, tokens, or sensitive customer data in the planning artifacts.
SkillSpector
By NVIDIA
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
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.