AgentDB Vector Search
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill utilizes
npx agentdb@latestto install and run tools from the npm registry. The package originates from an untrusted source ('ruvnet'). - REMOTE_CODE_EXECUTION (MEDIUM): The use of
npxfor package execution fetches and runs remote code. - PROMPT_INJECTION (LOW): The RAG implementation example shows an indirect prompt injection surface. Evidence Chain: 1. Ingestion points: Data is processed via AgentDB storage and retrieval methods as seen in SKILL.md. 2. Boundary markers: No delimiters or 'ignore' instructions are present in the provided LLM prompt template example. 3. Capability inventory: The skill facilitates LLM generation (
llm.generate) based on retrieved data. 4. Sanitization: No input sanitization or escaping is used for external context before it is interpolated into the prompt.
Audit Metadata