orchestrating-datacloud

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

• Third-party content exposure detected (high risk: 0.80). The skill's setup and runtime steps explicitly fetch and use a public community plugin (scripts/bootstrap-plugin.sh and references/plugin-setup.md clone https://github.com/Jaganpro/sf-cli-plugin-data360.git and even suggest curling raw GitHub content), and the skill expects the linked sf data360 runtime and its command outputs (and generated manifests that read plugin files) to be consumed as part of its workflow, meaning untrusted third‑party content can influence tool behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime/bootstrap steps clone and install a community CLI plugin from https://github.com/Jaganpro/sf-cli-plugin-data360.git (and even suggests a curl | python invocation of https://raw.githubusercontent.com/Jaganpro/sf-skills/main/tools/install.py), which fetches remote code that is compiled/linked and executed as a required runtime dependency.