google-cloud-vision-automation

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies (LOW): The skill instructions require the user to add an external MCP server endpoint (https://rube.app/mcp). This domain is not on the list of trusted external sources. While this is central to the skill's purpose for interacting with Composio, it establishes a dependency on third-party infrastructure that controls the tools available to the agent.
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and act upon data from an external source through a dynamic discovery mechanism.
  • Ingestion points: Data enters the context via the RUBE_SEARCH_TOOLS response, which provides tool schemas and execution plans.
  • Boundary markers: Absent. The skill does not define delimiters or provide instructions to the agent to ignore potentially malicious content within the discovered schemas.
  • Capability inventory: The skill has access to high-privilege operations including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (which supports run_composio_tool()).
  • Sanitization: Absent. There is no evidence of validation or sanitization of the tool arguments or schemas returned by the remote server before they are used in execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 01:43 AM