httpie

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly makes HTTP requests to arbitrary public URLs as part of its core workflow (see SKILL.md and references/commands.md), provides reusable helpers that call user-supplied URLs in templates/httpie-fallback.sh, and runs/validates live requests and parses responses in scripts/probe_httpie.py, so untrusted third‑party web content can be fetched and ingested at runtime and could influence subsequent actions.