salesforce-development

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

• Third-party content exposure detected (high risk: 0.90). The skill's installation workflow (README.md and .claude/INSTALL.md) explicitly instructs the agent to git-clone and run files from a public GitHub repo (https://github.com/xixiaofinland/sf-workflow), so the agent would fetch and execute untrusted third-party content that can change its behavior or carry embedded instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's install instructions and OpenCode plugin entry cause the agent to fetch and load remote skill code from https://github.com/xixiaofinland/sf-workflow (git+https://github.com/xixiaofinland/sf-workflow.git), and that fetched repository contains the skill files that directly define/alter agent prompts and behavior at runtime, making it a required remote dependency that can control execution.