rabbit-inspect
Warn
Audited by Snyk on Mar 18, 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). Flagged: SKILL.md's ARRIVE phase mandates capturing real screenshots from arbitrary target URLs via Glimpse (e.g., the "uv run ... glimpse matrix" / "glimpse capture" commands with "{target_url}") and explicitly requires the agent to read and act on those screenshots, which exposes it to untrusted public web content that can influence decisions and follow‑up actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata