bluebubbles

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements legitimate messaging functionality for the BlueBubbles platform. All defined actions (send, react, edit, unsend, reply) are consistent with the stated purpose of the skill.
  • [SAFE]: No prompt injection techniques, such as attempts to bypass safety filters or override system instructions, were detected in the skill instructions.
  • [SAFE]: There is no evidence of data exfiltration or unauthorized access to sensitive information. While the sendAttachment tool can access local files via a file path, this is a standard and necessary feature for a messaging integration.
  • [SAFE]: The skill does not download or execute remote code, and it does not define any external software dependencies in the provided content.
  • [SAFE]: No obfuscation techniques, such as Base64 encoding of commands or hidden Unicode characters, were found in the file.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 AM