doppler-marketing-automation-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection through external data ingestion from the Doppler API.
- Evidence Chain: 1. Ingestion points: Tool outputs from RUBE_SEARCH_TOOLS and RUBE_MULTI_EXECUTE_TOOL. 2. Boundary markers: Absent; no delimiters are defined to separate tool data from agent instructions. 3. Capability inventory: High-privilege actions including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (arbitrary tool/code execution). 4. Sanitization: Absent; no validation or escaping logic is prescribed for the ingested content.
- [External Reference] (SAFE): The skill references an external MCP server (https://rube.app/mcp). While this is a third-party service, it is the intended primary purpose of the skill and does not involve unauthorized local execution.
Audit Metadata