PII Redactor
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed PII redaction guardrail that sends draft responses to a user-configured local or internal service before delivery.
Install only if you want every outbound response checked for PII. Keep CLAWGUARD_URL pointed to localhost or an internal HTTPS service you operate, protect CLAWGUARD_TOKEN, do not expose the server publicly, and verify the PyPI package/source before using it with sensitive or production data.
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
66/66 vendors flagged this skill as clean.