productlane-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and acting upon data from Productlane.
- Ingestion points: Data enters the agent's context through the Productlane API via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH calls (SKILL.md).
- Boundary markers: Absent; there are no specific delimiters or instructions provided to the agent to disregard embedded instructions within the retrieved Productlane data.
- Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH to perform tool operations and remote script execution (SKILL.md).
- Sanitization: Absent; the skill does not specify any validation, filtering, or escaping of the content fetched from external Productlane resources.
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server connection to https://rube.app/mcp. This endpoint belongs to a well-known service used for managed tool orchestration.
Audit Metadata