better-stack-automation

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its reliance on untrusted data processed at runtime.
  • Ingestion points: The agent fetches tool slugs, input schemas, and execution plans dynamically from the RUBE_SEARCH_TOOLS command (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the fetched tool descriptions or schemas (SKILL.md).
  • Capability inventory: The skill allows for the execution of discovered tools via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, providing a path for the agent to act on injected instructions (SKILL.md).
  • Sanitization: No explicit validation or sanitization of the external tool metadata is present in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill configuration requires the addition of an external MCP server at https://rube.app/mcp to function (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:36 AM