bluebubbles

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the processing of external message content and chat metadata, creating a surface for indirect prompt injection.
  • Ingestion points: Incoming message text and message IDs from the BlueBubbles integration (SKILL.md).
  • Boundary markers: None identified; instructions do not specify delimiters or guidelines to distinguish data from instructions.
  • Capability inventory: Includes the ability to read local files through the path parameter in the sendAttachment action and transmit data via the messaging channel (SKILL.md).
  • Sanitization: No input validation or sanitization mechanisms are described for processed message content or file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:29 PM
Security Audit — agent-trust-hub — bluebubbles