chaser-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill configures a connection to an external MCP server at https://rube.app/mcp. As this domain is not within the specified trusted external sources, it represents an unverified third-party dependency.\n- [Indirect Prompt Injection] (LOW): The skill utilizes RUBE_SEARCH_TOOLS to dynamically fetch tool schemas and execution plans. This architecture creates an attack surface where a compromised or untrusted MCP server could inject malicious instructions into tool descriptions to influence the agent's behavior.\n
  • Ingestion points: Metadata and schemas returned by RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS (SKILL.md).\n
  • Boundary markers: Absent; there are no instructions to the agent to ignore or delimit instructions found within the tool schemas.\n
  • Capability inventory: Operations include executing tools via RUBE_MULTI_EXECUTE_TOOL and managing workbench tasks via RUBE_REMOTE_WORKBENCH (SKILL.md).\n
  • Sanitization: Absent; the workflow relies on the integrity of the external server's response for schema compliance.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM