AgentDB Advanced Features

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the agentdb package via npx and the agentic-flow library. These resources are hosted on official registries (npm) and are part of the author's (ruvnet) established ecosystem.
  • [COMMAND_EXECUTION]: Documentation includes CLI examples for npx, sqlite3, and node. It also provides troubleshooting commands such as sudo ufw allow 4433/udp for manual firewall configuration by a user.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and retrieve arbitrary data.
  • Ingestion points: Data is ingested through the adapter.insertPattern method as shown in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are demonstrated in the code snippets.
  • Capability inventory: The skill facilitates local file system access for database storage (dbPath) and network communication for peer-to-peer synchronization (QUICSync).
  • Sanitization: No specific sanitization or validation of the content within the patterns is presented in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 07:39 PM