blog-post
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Step 2 "Research and gather sources" explicitly instructs the agent to "fetch URLs" and "read every source completely" (including pasted text), meaning it ingests untrusted open/public web content that will directly shape outlines and writing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata