deep-interview

Warn

Audited by Snyk on Aug 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). deep-interview ingests outsider-authored free text directly from the user’s supplied {{ARGUMENTS}}/initial idea and each round’s rcs question response (answers[0].answer), using that text throughout the required workflow’s Socratic clarification loop before writing specs and handing off.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 11:36 AM
Issues
1
Security Audit — snyk — deep-interview