world-voice

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's Step 3 Question 1 explicitly asks the user to "Share a piece of writing — a social post, email, essay, anything — paste it here," so the agent ingests arbitrary user-generated/untrusted content (including public social posts) and uses that content to drive analysis and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 09:28 PM