voice-extractor

Warn

Audited by Snyk on Mar 8, 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 Context Loading Gates require collecting writing samples — explicitly listing LinkedIn posts and website copy — and later phases (Phase 3 and Validation Test) instruct the agent to scan, quote, and base outputs on those samples, so it ingests untrusted/public user-generated content that can directly influence subsequent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 11:29 PM