saleor-graphql

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly fetches live public documentation pages from https://docs.saleor.io/... at runtime (“Fetch live docs” steps), and that fetched free-form web page text is ingested into the agent’s LLM context, creating an outsider-source prompt-injection risk.

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 live Saleor docs at runtime (https://docs.saleor.io/docs/developer/api-reference and https://docs.saleor.io/docs/developer/api-conventions), and those fetched documents are required and used to shape the agent's prompts/implementation behavior, so they are runtime external dependencies that control the agent.