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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata