DeepRead PII Redaction
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is coherent and disclosed, with the main consideration being that original sensitive documents are sent to DeepRead for redaction.
Install only if you are comfortable sending the original unredacted documents to DeepRead’s hosted service. Use a dedicated API key if possible, keep it out of shared configs, use HTTPS webhooks you control, and review DeepRead’s privacy, retention, and compliance terms before processing medical, legal, financial, or other regulated 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
56/56 vendors flagged this skill as clean.