prd-create

Warn

Audited by Snyk on Aug 13, 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). Outsider-authored free text enters via the user’s “feature idea” in Step 1 (AskUserQuestion) and is then written into GitHub issues/PRD files that are later read by the skill’s optional reviewer agents (Step 1.5→Step 166-174) and potentially handed to uzi (Step 219-231); these agents ingest the resulting PRD text at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 13, 2026, 05:40 PM
Issues
1
Security Audit — snyk — prd-create