webscraping-ai-automation
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and process external web content via the webscraping_ai toolkit, which serves as an ingestion point for untrusted data into the agent's context. The skill instructions lack specific boundary markers or 'ignore' directives to help the agent distinguish between legitimate data and potential embedded instructions. Furthermore, the skill provides the agent with powerful capabilities, including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, which could be misused if the agent is manipulated by instructions hidden within the scraped content. There are no mentions of sanitization or filtering logic for the ingested data.
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server at rube.app. This service is part of the Composio ecosystem and provides the underlying tool integrations necessary for the skill's operation.
Audit Metadata