designing-agent-tools

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly documents using a "web_search" tool in references/programmatic-tool-calling.md and describes agents reading/searching external docs and web pages (e.g., "Web Search with PTC" and "Progressive disclosure via Skills" in references/iterative-tool-design.md and SKILL.md), which means the agent is expected to fetch and interpret open/public third‑party content that could influence its tool calls and behavior.