confluence

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

• Third-party content exposure detected (high risk: 0.80). The skill clearly ingests user-generated Confluence page content via the Confluence REST API (see SKILL.md and references/commands.md pages/ search/ export/ hierarchy commands that read body.storage.value) and also submits diagram code to the public kroki.io renderer, so untrusted third‑party content can be read and used to drive publishing/upsert actions and link/label decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisites explicitly instruct running a remote installer that fetches and executes code (curl -sSfL https://raw.githubusercontent.com/jorgemuza/orbit/main/install.sh | sh), which is a runtime external dependency that executes remote code and is required to install the orbit CLI.