ai-context-generator

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

• Third-party content exposure detected (high risk: 0.75). The skill reads and ingests runtime text from outsider-authored project files—e.g., README.md and AGENTS.md via analyzeProject() (fs.readFileSync(readmePath/agentsPath, 'utf-8'))—and then writes that derived content into .ai-context/ files that the agent will load into its LLM context.