automations-toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an audit workflow that retrieves and analyzes the source code of existing LeanIX automations, creating a potential surface for indirect instructions to influence the agent.
- Ingestion points: The agent ingests external script content through the
mcp__leanix__get_automation_scripttool as part of the audit process described inreferences/WORKSPACE-ANALYSIS.md. - Boundary markers: The instructions do not provide explicit boundary markers or guidance to ignore instructions embedded within the analyzed scripts.
- Capability inventory: The agent is granted
Write,Edit, and variousmcp__leanix__*tools, allowing it to modify automations and workspace data. - Sanitization: There are no instructions for sanitizing or validating the content of retrieved scripts before the agent performs its analysis.
Audit Metadata