cleanup-deals

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data from HubSpot CRM records.
  • Ingestion points: Deal data and properties are retrieved from the HubSpot API using the hubspot-api-client.
  • Boundary markers: No specific delimiters or instructions are provided to isolate external data from the agent's command logic.
  • Capability inventory: The skill enables the agent to delete CRM records and modify deal stages, which could be abused if malicious instructions are embedded in deal fields.
  • Sanitization: There is no explicit validation or sanitization of deal property values before they are used in the cleanup logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 04:20 AM