AgentDB Memory Patterns

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx agentdb@latest to execute the latest version of the agentdb package from the npm registry.
  • [COMMAND_EXECUTION]: Multiple CLI commands are provided for database initialization, plugin management, and starting MCP services for integration with environments like Claude Code.
  • [PROMPT_INJECTION]: As a memory-management skill, it introduces an indirect prompt injection surface where stored content could influence future agent behavior. 1. Ingestion points: Interaction data ingested via the adapter.insertPattern and db.storeMemory methods mentioned in SKILL.md. 2. Boundary markers: The provided examples do not demonstrate the use of delimiters or guardrail instructions when retrieving and using memory content. 3. Capability inventory: The skill enables the agent to interact with the file system for database storage and execute CLI operations. 4. Sanitization: No explicit data sanitization or validation of retrieved memory is included in the demonstrated patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 07:18 AM
Security Audit — agent-trust-hub — AgentDB Memory Patterns