pipedrive-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the Rube MCP server at https://rube.app/mcp. This is an established endpoint for Composio's Rube MCP bridge and is documented here as the standard method for accessing Pipedrive automation tools.\n- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it retrieves and processes untrusted data from Pipedrive CRM records.\n
  • Ingestion points: External content enters the agent's context through tools like PIPEDRIVE_GET_ALL_NOTES, PIPEDRIVE_GET_DETAILS_OF_A_PERSON, and PIPEDRIVE_GET_DETAILS_OF_A_DEAL.\n
  • Boundary markers: The skill does not define specific delimiters or provide instructions to the agent to disregard potentially malicious commands embedded within retrieved records.\n
  • Capability inventory: The skill has extensive write and update permissions, including the ability to manage deals, contacts, organizations, and activities within the linked Pipedrive account.\n
  • Sanitization: The retrieved data is processed directly by the agent without any explicit sanitization or validation logic defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM