eventee-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION] (LOW): The skill initiates network requests to rube.app and references composio.dev. Neither domain is included in the trusted source whitelist.
  • [PROMPT_INJECTION] (LOW): The skill possesses a vulnerability surface for indirect prompt injection.
  • Ingestion points: The skill retrieves and processes event data from the Eventee platform via tool outputs.
  • Boundary markers: Absent; the instructions do not provide delimiters or instructions to the agent to ignore or isolate embedded instructions in the ingested data.
  • Capability inventory: The agent has access to RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, enabling it to execute a variety of tools based on processed input.
  • Sanitization: Absent; no input validation, escaping, or filtering of the retrieved data is specified.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill requires the configuration of an external MCP server at https://rube.app/mcp, which is an unverifiable third-party dependency.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:47 PM