sf-datacloud

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

• Third-party content exposure detected (high risk: 0.90). The skill's setup and runtime steps (e.g., scripts/bootstrap-plugin.sh and references/plugin-setup.md) explicitly clone and install a community sf-cli-plugin-data360 from GitHub (https://github.com/Jaganpro/sf-cli-plugin-data360.git) so the agent fetches and executes untrusted third-party code that can change CLI behavior and thereby influence subsequent decisions/actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly performs runtime installs that fetch and execute remote code—e.g., scripts/bootstrap-plugin.sh clones the plugin from https://github.com/Jaganpro/sf-cli-plugin-data360.git and references/plugin-setup.md suggests running curl -sSL https://raw.githubusercontent.com/Jaganpro/sf-skills/main/tools/install.py | python3 ...—so these URLs are used at runtime to download and run required external code.