AgentDB Vector Search
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx agentdb@latest (e.g., fetching and executing the agentdb package from the npm registry at https://registry.npmjs.org/agentdb) at runtime, which downloads and runs remote code that the skill depends on, so this external fetch can directly execute code and is therefore a runtime risk.
Audit Metadata