perplexityai-automation

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires the configuration of an external MCP server at https://rube.app/mcp. This source is not part of the verified trusted source list, creating a runtime dependency on unverified infrastructure.\n- [COMMAND_EXECUTION] (MEDIUM): The skill uses RUBE_MULTI_EXECUTE_TOOL to perform actions based on schemas discovered at runtime. This allows the remote server to dictate the agent's available actions and arguments.\n- [PROMPT_INJECTION] (MEDIUM): The skill is vulnerable to Indirect Prompt Injection (Category 8) because it treats remote tool discovery as authoritative.\n
  • Ingestion points: RUBE_SEARCH_TOOLS response content.\n
  • Boundary markers: Absent; the agent is instructed to "use exact field names and types from the search results" without delimitation.\n
  • Capability inventory: RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH provide execution and workflow automation capabilities.\n
  • Sanitization: Absent; the skill lacks any validation or filtering of the schemas returned by the remote server.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:32 PM