api4ai

Warn

Audited by Snyk on Mar 4, 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 SKILL.md explicitly documents actions such as "Detect Objects from URL" and instructions for running actions/proxy requests that ingest and analyze content at arbitrary external URLs (e.g., image URLs), so the agent will fetch and interpret untrusted third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:58 AM