marketing-referral
Warn
Audited by Snyk on Apr 27, 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 workflow (see "Starting Context Router" and Response Protocol step 1–2 in SKILL.md) explicitly requires using a "live URL audit" / "read ... live site" as part of the standard context-reading sequence, so the agent will fetch and interpret content from public websites (untrusted third-party sources) that can materially influence decisions and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata