bluebubbles

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions define a process for ingesting external data via webhooks, creating a surface for indirect prompt injection. • Ingestion points: The webhook handler in extensions/bluebubbles/src/monitor.ts processes external JSON payloads from the BlueBubbles server. • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating inbound message content into prompts. • Capability inventory: The plugin includes capabilities to send messages (sendMessageBlueBubbles), send reactions, and perform network requests (blueBubblesFetchWithTimeout). • Sanitization: While the skill suggests defensive normalization for sender IDs, it lacks explicit guidance for sanitizing or escaping message content before it is processed by the core pipeline.
  • [NO_CODE]: The skill package contains no executable scripts, binaries, or configuration files other than the SKILL.md file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:24 AM