AgentDB Vector Search
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (HIGH): The skill uses
npx agentdb@latestto download and run code from an untrusted NPM package at runtime. - [REMOTE_CODE_EXECUTION] (HIGH): Executing unpinned remote packages from an untrusted organization (
ruvnet) vianpxpresents a significant code execution risk. - [PROMPT_INJECTION] (HIGH): The RAG implementation in
SKILL.mdis vulnerable to indirect prompt injection. Ingestion point:db.searchSimilarretrieves untrusted context. Boundary markers: Absent in prompt construction. Capability inventory: Filesystem write access and CLI command execution. Sanitization: None applied to retrieved data before interpolation into the prompt. - [COMMAND_EXECUTION] (MEDIUM): The skill triggers CLI-based database operations (init, query, import, stats) through the unverified
agentdbpackage.
Recommendations
- AI detected serious security threats
Audit Metadata