implementing-email-sandboxing-with-proofpoint

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's runtime scripts (scripts/agent.py:get_tap_threats and scripts/process.py:ProofpointTAPClient/_get) and SKILL.md explicitly fetch message/sandbox data from the Proofpoint TAP API (e.g., https://tap-api-v2.proofpoint.com/v2/siem/all and related endpoints), which contain untrusted/user-generated email and URL content that the agent parses and uses to set verdicts, quarantine actions, alerts, and other decisions—so third-party content can materially influence behavior.