Autonomous Code Review
Security checks across malware telemetry and agentic risk
Overview
This is a small instruction-only code review skill with disclosed, purpose-aligned repository scanning examples and no hidden executable behavior.
Install this as a code-review prompt aid, not as a standalone scanner. Before enabling the repo-wide, CI, or pre-commit examples, confirm you are comfortable sending that code to the configured OpenClaw/model tooling and store any API key only in the intended CI secret store.
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.