wiki
Warn
Audited by Snyk on Apr 10, 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). SKILL.md's "ingest <path|url>" step explicitly uses the WebFetch tool to retrieve arbitrary URLs from the open web (e.g., "ingest https://example.com/article"), and the required "compile" workflow then reads and processes that fetched content to create/update pages, extract entities, and modify links — meaning untrusted third‑party content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata