composio-search-automation

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to a remote MCP endpoint (https://rube.app/mcp) provided by the vendor to access search automation tools.
  • [PROMPT_INJECTION]: Exhibits an indirect prompt injection surface by ingesting tool schemas and recommended execution plans from the RUBE_SEARCH_TOOLS tool.
  • Ingestion points: Results from RUBE_SEARCH_TOOLS (SKILL.md).
  • Boundary markers: None.
  • Capability inventory: Executes tools via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH (SKILL.md).
  • Sanitization: None mentioned.
  • [COMMAND_EXECUTION]: Provides patterns for executing remote tools and workbench operations based on schemas and plans retrieved from the search index at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:24 AM
Security Audit — agent-trust-hub — composio-search-automation