api-sports-automation

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill mandates the use of an external MCP server at https://rube.app/mcp. This domain is not a verified trusted source and the instructions suggest a 'no keys needed' setup which avoids standard authentication controls.
  • [REMOTE_CODE_EXECUTION] (HIGH): The skill uses RUBE_MULTI_EXECUTE_TOOL which permits the agent to execute actions based on tool schemas retrieved from an external server. This bypasses local control of allowed actions.
  • [COMMAND_EXECUTION] (HIGH): The inclusion of RUBE_REMOTE_WORKBENCH implies the capability to perform arbitrary operations in a remote environment, which is a high-privilege capability that should be restricted.
  • [PROMPT_INJECTION] (HIGH): Vulnerable to indirect prompt injection through data processed from API Sports. 1. Ingestion Points: Data retrieved from sports API tools. 2. Boundary Markers: Absent; no instructions for the agent to ignore instructions embedded in the API data. 3. Capability Inventory: Includes RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. 4. Sanitization: Absent; no logic provided to escape or validate external content before execution.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:24 PM