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
pathparameter in thesendAttachmentaction 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