Security audit
Talamus Memory
Security checks for vulnerabilities and agentic risk
Overview
This skill provides a disclosed local memory workflow and requires user approval for installation, LLM use, broad ingestion, and transcript capture.
Before installing or using it, confirm which Talamus brain should be active and review any proposed ingestion or session-capture steps. Do not approve repository scans, transcript capture, broad memory scopes, or secret-inclusive ingestion unless you intend that data to be stored locally and possibly used in later retrieval.
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.