slides-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2.5 Research Workflow and examples explicitly perform targeted web searches and invoke the ui-ux-pro-max search script (e.g., "Conduct targeted web search", "python3 ~/.claude/skills/ui-ux-pro-max/scripts/search.py ...", and the example "Claude: [Conducts web search for current AI benchmarks]") which ingests open/public third‑party content (web pages, papers, URLs) that the agent is expected to read and use in the presentation, so it can introduce untrusted/user-generated content into the agent's workflow.