Is ksemaj/lily-memory-5-0-0 safe?

https://github.com/openclaw/skills/tree/main/skills/ksemaj/lily-memory-5-0-0

96
SAFE

Lily Memory is a legitimate persistent memory plugin for OpenClaw agents that provides SQLite-based storage with FTS5 search and optional Ollama vector embeddings. The plugin implements proper security practices including SQL injection protection and input validation, with no signs of malicious behavior.

Category Scores

Prompt Injection 100/100 · 30%
Data Exfiltration 98/100 · 25%
Code Execution 85/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 90/100 · 5%

Findings (3)

LOW Shell Command Execution -15 ▶

Plugin executes sqlite3 CLI commands through Node.js execSync. This is legitimate functionality for database operations, and the code implements proper SQL injection protection via escapeSqlValue() function.

INFO Conversation Data Storage -10 ▶

As a memory plugin, this skill stores conversation facts and user data in SQLite databases. While this is the intended functionality, users should be aware that sensitive information may be persisted locally.

INFO Canary File Access -2 ▶

Monitoring detected access to honeypot files during installation. This appears to be from the monitoring system itself rather than the skill, and all files remained intact.