blog-persona
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's Create Workflow Step 6 ("Voice Samples") explicitly asks for 1–3 user-provided URLs and instructs the agent to read each URL and extract tone/readability metrics, so it ingests untrusted third-party web content that can change persona settings and thus influence generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata