design-harness-agent-skill
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the “Filing Sources” workflow, when the user “drops URLs/PDFs” the agent reads the source material and extracts key claims to create markdown cards in
sources/, meaning outsider-authored text supplied via URLs/PDFs is ingested at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata