astro-starlight

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

• Third-party content exposure detected (high risk: 0.75). The workflow only instructs the agent to analyze the local Starlight codebase and query Starlight docs (via Context7/Exa and mcp__context7__query-docs), which are public/third-party documentation sources whose fetched text can be ingested into the agent’s LLM context as free-form prose.