saleor-setup

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 to fetch public web pages from docs.saleor.io and github.com (e.g., “Fetch live docs” and “Web-search … for latest Compose file”), and those fetched page text would be ingested into the agent’s LLM context.

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 documentation (e.g., https://docs.saleor.io/docs/developer/getting-started/architecture) at runtime to inform implementation decisions, so external content would directly control the agent's prompts/instructions and is a required dependency.