segment-audience

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from external CRM and marketing platforms, creating an attack surface for indirect prompt injection.
  • Ingestion points: Behavioral, demographic, and engagement data are retrieved from external CRMs and email platforms in Step 2 of the process.
  • Boundary markers: No specific delimiters or instructions to ignore instructions embedded within the ingested data are defined.
  • Capability inventory: The skill has the ability to write execution results to local log files and create or update audience segments on external platforms via API calls.
  • Sanitization: The instructions do not define any sanitization or validation procedures for the data retrieved from external sources before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 05:27 PM