webscraping-ai-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • External Dependencies (MEDIUM): The skill instructs users to configure an MCP server using the endpoint https://rube.app/mcp. This domain is not included in the list of trusted external sources. Since the server provides the tool definitions and schemas, it exerts significant control over the agent's available actions.
  • Indirect Prompt Injection (LOW): The skill's primary function is web scraping, which involves processing data from arbitrary external websites.
  • Ingestion points: Data retrieved from websites via the webscraping_ai toolkit.
  • Boundary markers: None specified; there are no instructions for the agent to treat scraped content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The skill utilizes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, providing the agent with the ability to execute a wide range of follow-up tasks based on the scraped input.
  • Sanitization: No evidence of sanitization, filtering, or validation of the ingested web content.
  • Dynamic Execution (MEDIUM): The workflow relies on RUBE_SEARCH_TOOLS to dynamically discover tool slugs and input schemas at runtime. This 'just-in-time' discovery mechanism allows the remote server to modify the agent's execution logic dynamically, which could be exploited to trigger unintended tool calls via RUBE_MULTI_EXECUTE_TOOL.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:18 PM