better-stack-automation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for interacting with Better Stack through the Rube MCP gateway by Composio.
  • [EXTERNAL_DOWNLOADS]: Referenced resources include documentation on "composio.dev" and the "rube.app" MCP endpoint, which are established services for tool-calling integration.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection. 1. Ingestion points: Tool schemas and descriptions are fetched from the Rube MCP server via "RUBE_SEARCH_TOOLS" in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: "RUBE_MULTI_EXECUTE_TOOL" and "RUBE_REMOTE_WORKBENCH" in SKILL.md allow execution of discovered tools. 4. Sanitization: Absent. This surface is inherent to the Model Context Protocol (MCP) design for tool discovery.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:43 PM
Security Audit — agent-trust-hub — better-stack-automation