brand-voice

Warn

Audited by Snyk on Mar 23, 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). SKILL.md explicitly instructs the agent to "Use WebSearch to find" example content under "If Description Provided (Option B)" and also accepts pasted URLs/file paths in "Option A
  • Existing Content", so the skill will fetch and interpret public third‑party web content that can influence generated voice rules and downstream actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 02:43 PM
Issues
1