NYC

asc-localize-metadata

Warn

Audited by Snyk on Feb 19, 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.md workflow explicitly downloads App Store Connect localization data via commands like "asc localizations download" (Step 2) and then feeds those user-provided app metadata strings to an LLM for translation (Step 3), meaning untrusted, developer-authored content from a third-party service is read and can influence subsequent actions (uploads), enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 10:53 AM