investor-audits

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to read and parse incoming auditor/investor emails ("Pending requests are tracked via the audits Gmail label
• emails ARE the tracker" and the "Parse the Request" workflow), meaning it ingests untrusted third-party (user-generated) content that directly drives decision-making and response drafting.