engineering-technical-writer
Warn
Audited by Snyk on Apr 7, 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.md Workflow Process (Step 1: "Read existing GitHub issues and support tickets") explicitly instructs the agent to ingest public, user-generated content (GitHub issues/support tickets), which the agent will read and use to shape documentation decisions and actions, creating a realistic avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata