absolute-human
Warn
Audited by Snyk on Apr 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The DISCOVER phase explicitly instructs agents to perform "Web Research (when codebase context is insufficient)"—i.e., consult external public documentation, best-practice articles, and similar web resources—which the agent will read and incorporate into plans and execution (SKILL.md DISCOVER section), creating a clear vector for untrusted third‑party content to influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata