saleor-deploy

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the runtime workflow to “Web-search” and “Fetch” live public documentation pages (e.g., docs.saleor.io and GitHub) and then use that fetched readable text as LLM context, which is outsider-authored free text from the public web.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs fetching https://github.com/saleor/saleor-platform at runtime to use the repository's Docker Compose/configuration as the deployment reference, so remote content would directly shape the agent's instructions and outputs.