dialog

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill ingests and analyzes user-generated interview responses from an external participant pool (see "Participants are from a general population pool" and the tools interview_read and dialog_analyze that read full interview transcripts), so the agent will read untrusted third-party content that could contain injected instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:59 AM