Security audit
SDD Plan Human Verify
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is not malware, but it prepares checklist commands that another verifier may run automatically, including installs, services, and database migrations.
Install only if you will review the generated spec-human-verify.md before running any follow-on verifier. Pay special attention to generated [AUTO] and [AUTO/SERVICE] commands involving package installs, database migrations, deletes, cloud/account actions, sudo, secrets, or long-running services.
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.
Static analysis
No suspicious patterns detected.