Threshold Keel
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed safety guardrail skill that asks agents to get approval before risky actions and can use an optional CLI/cloud audit trail.
Install this only if you want an agent-wide approval and audit layer for risky actions. Before enabling CLI or cloud mode, make sure you trust the `threshold-keel` pip package and understand that action metadata may be stored locally under `~/.keel/` and, if `KEEL_CLOUD_API_KEY` is set, synced to Threshold Cloud.
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
62/62 vendors flagged this skill as clean.