api-design

Warn

Audited by Snyk on Feb 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: 0.90). The skill's examples (examples/orchestkit-api-design.md and SKILL.md) show a POST /api/v1/analyze endpoint that accepts arbitrary external URLs and starts a background run_workflow_task which detects content type and extracts/analyzes the fetched webpage, meaning the agent will fetch and interpret untrusted third‑party web content as part of its workflow (possible indirect prompt injection).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 04:27 PM