referral-program

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md Research Methodology explicitly requires the agent to "Use WebSearch extensively" to ingest public referral program case studies and benchmarks, which the agent is expected to read and incorporate into its program design—exposing it to untrusted third‑party web content that could alter decisions or actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 04:42 PM