Security audit
LYGO Sanctuary Guardian
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local-only receipt and hash verification helper with consent-gated file writes and no evidence of hidden network, shell, publishing, or destructive behavior.
Treat this as a local integrity/receipt generator, not as real security infrastructure. Do not place secrets in the truth, light, seed, or node fields because those values can be stored in generated JSON artifacts. Only use --write with paths you intend to create or overwrite.
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
Static analysis
No suspicious patterns detected.