pipedrive-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to connect to a remote MCP server hosted at https://rube.app/mcp. This is a necessary configuration for the skill's primary function of CRM automation via Composio.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8).
  • Ingestion points: The agent ingests untrusted data from the Pipedrive CRM through tools such as PIPEDRIVE_GET_ALL_NOTES, PIPEDRIVE_SEARCH_PERSONS, and PIPEDRIVE_GET_DETAILS_OF_A_DEAL (referenced in SKILL.md).
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat external CRM data as untrusted or to ignore embedded instructions within that data.
  • Capability inventory: The agent possesses significant write capabilities, including the ability to modify records (PIPEDRIVE_UPDATE_A_DEAL), create new entities (PIPEDRIVE_ADD_A_PERSON), and execute CRM workflows.
  • Sanitization: There is no evidence of client-side sanitization or validation of the data retrieved from the CRM before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:34 AM