implementing-as-tachikoma

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflows (e.g., references/WORKFLOWS.md "Step3: 最新仕様の確認" and references/TOOLS.md which lists WebFetch and search MCPs like context7/kagi/firecrawl) instruct the agent to fetch and read public web pages and documentation as a necessary part of implementation decisions, exposing it to untrusted third-party content that can materially influence tool use and actions.