kelly-agent-builder

Warn

Audited by Snyk on Aug 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the app’s browser UI loads and renders Busabase record text (e.g., agent name, trigger_description, owning_team, and status/usage fields) via getProvider()->busabaseProvider.getState() and provider.getState()->readAllRecords("agents"), which ingests outsider-authored free text from the agents Base without first selecting a specific item beyond “the catalog/table”.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 25, 2026, 10:35 AM
Issues
1
Security Audit — snyk — kelly-agent-builder