Security audit
redact-pii
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts are coherent operational skills with disclosed use of local scripts, credentials, APIs, and persistence for their stated admin, observability, documentation, and development workflows.
Install only if you trust the publisher and intend to use these operational workflows. Before running helper scripts, review the credentials they require, prefer least-privilege API tokens, avoid storing secrets in shared memory, and use the confirmation/dry-run paths for moderation, email, release, dashboard, and monitor changes.
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.
Static analysis
No suspicious patterns detected.