mempalace-cognition
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
llama-serverto provide semantic search capabilities and a Python script (MemPalace_Manager.py) located in the user's~/.geminidirectory to manage memory entries. These commands are necessary for the skill's stated functionality and operate entirely within the local environment. - [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill uses standard local file paths and does not involve untrusted remote code or network connections to external domains.
Audit Metadata