BlueBubbles

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a webhook handler that ingests data from external BlueBubbles servers, creating a potential surface for indirect injection.
  • Ingestion points: extensions/bluebubbles/src/monitor.ts processes inbound JSON payloads.
  • Boundary markers: None specified for the message content; however, the documentation advises defensive normalization of metadata.
  • Capability inventory: The plugin includes capabilities to send messages, reactions, and download attachments via defined internal helpers.
  • Sanitization: The instructions recommend defensive normalization of sender and chat IDs, while message content is routed to the core reply pipeline for further processing.
  • [DATA_EXPOSURE]: The skill defines configuration keys for serverUrl and password. These are documented as part of the required configuration schema for the plugin and do not contain hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 05:57 PM