openchoreo-setup

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime workflow explicitly fetches and reads public documentation pages (via scripts/fetch-page.sh which pulls openchoreo.dev/llms.txt and the linked docs and may fetch raw GitHub READMEs like https://github.com/openchoreo/...) and treats those fetched guides as "the source of truth" whose instructions the agent must follow to perform installs, so untrusted third‑party content can directly influence tool use and next actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's fetch-page.sh is invoked at runtime and uses curl to retrieve https://openchoreo.dev/llms.txt (and then the docs pages/URLs it points to, e.g. raw content under https://raw.githubusercontent.com/openchoreo/openchoreo.github.io/main), and those fetched guides are treated as the "source of truth" that the agent must follow—so remote content directly controls runtime instructions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill instructs the agent to "follow it end to end" to install/bootstraps OpenChoreo on local k3d or existing clusters, which entails running installation commands that modify the host (install binaries, create containers, change kubeconfigs, interact with cluster APIs) and may require elevated privileges even though it doesn't explicitly request sudo or user creation.