Agent Provenance
Security checks across malware telemetry and agentic risk
Overview
This instruction-only governance skill is transparent about managing provenance for agent memory and instruction files, with no hidden code or external data flow found.
Install this only if you are comfortable with an agent maintaining provenance headers, scheduling OpenClaw cron checks, and committing changes to instruction and memory files. Review git history and diff reports, and keep secrets out of provenance headers, contact notes, and commit messages.
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
64/64 vendors flagged this skill as clean.