sendbird-ai-chabot-automation

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): The skill provides tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, enabling the agent to perform complex operations within the Sendbird ecosystem.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): Users are directed to add an external third-party MCP server (https://rube.app/mcp), which introduces dependency on an external provider.
  • [PROMPT_INJECTION] (HIGH): The skill is vulnerable to Indirect Prompt Injection (Category 8). 1. Ingestion points: Data entering from Sendbird AI Chabot chat messages. 2. Boundary markers: Absent; no delimiters are used to separate chat data from instructions. 3. Capability inventory: Execution of high-privilege tool slugs via RUBE_MULTI_EXECUTE_TOOL. 4. Sanitization: Absent; no validation or escaping of external content is defined.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:43 PM