x-create
Warn
Audited by Snyk on Feb 21, 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 explicitly loads and "learns" user-provided reference posts from assets/templates/ (see Creation Workflow Step 1 and assets/templates/README.md) which are expected to contain copied public X/Twitter posts from arbitrary accounts, and the agent automatically reads and uses those third‑party/user‑generated texts to shape generation, enabling indirect prompt injection.
Audit Metadata