AgentDB Learning Plugins
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation suggests using
npx agentdb@latest, which downloads and executes theagentdbpackage from the npm registry. These resources are part of the vendor's (ruvnet) official toolkit. - [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing training data that could potentially contain adversarial content.
- Ingestion points: Data enters the system via the
adapter.insertPatternmethod as shown inSKILL.md. - Boundary markers: The provided code snippets do not implement specific boundary markers or instructions to ignore embedded commands within the training data.
- Capability inventory: The skill facilitates neural network training and inference via the
adapter.trainandadapter.retrieveWithReasoningmethods. - Sanitization: The snippets demonstrate passing raw JSON data to the storage and training functions without explicit sanitization.
- [COMMAND_EXECUTION]: The skill provides various CLI commands for managing plugins (e.g.,
create-plugin,list-templates). These are standard operational commands for the described toolset.
Audit Metadata