grant-proposal
Warn
Audited by Snyk on Apr 29, 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 explicitly requires ingesting the funder's publicly posted guidance as a required input ("Funder stated priorities (copy from their guidance — essential)") and directs the agent to explicitly align and act on that content (see "Funder Alignment Check" and multiple sections), so untrusted third‑party web content can directly influence the agent's outputs and decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata