orchestrating-swarms

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly spawn research/guide agent types that use WebFetch/WebSearch (see references/agent-types.md "claude-code-guide" and the Research agent entries) and the SKILL.md "Pattern 4: Research + Implementation" shows the agent inserting ${research.content} from those fetches into follow-up Task prompts, meaning untrusted public web content is read and can directly influence subsequent tool use and actions.