refine-issue

Warn

Audited by Snyk on Aug 26, 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). Source refine-issue reads outsider-authored free text at runtime by calling gh issue view <n> --json ... comments ... (and similarly Linear get_issue/list_comments) before selecting/confirming a specific item, so anyone who can create/submit an issue or comment can have their text ingested for author-checked “instruction vs context” steering.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 03:15 PM
Issues
1
Security Audit — snyk — refine-issue