synthesis-voice-profiler
Warn
Audited by Snyk on May 12, 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's Step 1 explicitly says "If the user provides URLs, fetch and read them," so the agent will ingest arbitrary user-provided public web pages (untrusted third-party content) and use that content to generate voice-profile instructions that influence downstream behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata