crm-icp-analysis

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive CRM data, including deal revenue, industry types, and personally identifiable information (PII) such as names and email addresses. This data access is expected behavior for a CRM analysis tool and is managed through vendor-specific HubSpot MCP tools.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from external CRM records and has access to powerful tools like Bash.
  • Ingestion points: Data is retrieved from HubSpot using hubspot__search_crm_objects and hubspot__get_crm_objects (SKILL.md).
  • Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the CRM data.
  • Capability inventory: The skill has access to Bash, Write, and mcp__cogny__create_finding tools.
  • Sanitization: No sanitization or validation of the ingested CRM content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 06:43 AM
Security Audit — agent-trust-hub — crm-icp-analysis