dynamic-content-personalizer

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (CSV exports, subscriber rows). It includes explicit instructions to treat this data as untrusted and not follow instructions embedded in field values.
  • [DATA_EXPOSURE]: The skill handles PII. It mandates a 'PII guard' step to prevent sensitive data from rendering in email bodies and prohibits echoing raw PII in output specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:28 PM
Security Audit — agent-trust-hub — dynamic-content-personalizer