stackbone-integrations

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a configuration guide for the Stackbone ecosystem, detailing the relationships between connectors, accounts, and workflows.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and MCP server endpoints hosted at docs.stackbone.ai. As these resources belong to the skill's official author (stackbone), they are categorized as safe vendor resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes an architecture for processing external data (e.g., email, cloud storage events). While this represents a data ingestion surface, the skill promotes safe practices such as dry-running mappings and using JSONata for structured data transformation. This behavior is intrinsic to the skill's primary purpose of managing integrations.
  • [DYNAMIC_EXECUTION]: The use of JSONata for event mapping is documented. JSONata is a declarative transformation language used for field mapping and does not constitute unsafe dynamic code execution in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:48 AM
Security Audit — agent-trust-hub — stackbone-integrations